Neural activity when people solve verbal problems with insight

Abstract

People sometimes solve problems with a unique process called insight, accompanied by an "Aha!" experience. It has long been unclear whether different cognitive and neural processes lead to insight versus noninsight solutions, or if solutions differ only in subsequent subjective feeling. Recent behavioral studies indicate distinct patterns of performance and suggest differential hemispheric involvement for insight and noninsight solutions. Subjects solved verbal problems, and after each correct solution indicated whether they solved with or without insight. We observed two objective neural correlates of insight. Functional magnetic resonance imaging (Experiment 1) revealed increased activity in the right hemisphere anterior superior temporal gyrus for insight relative to noninsight solutions. The same region was active during initial solving efforts. Scalp electroencephalogram recordings (Experiment 2) revealed a sudden burst of high-frequency (gamma-band) neural activity in the same area beginning 0.3 s prior to insight solutions. This right anterior temporal area is associated with making connections across distantly related information during comprehension. Although all problem solving relies on a largely shared cortical network, the sudden flash of insight occurs when solvers engage distinct neural and cognitive processes that allow them to see connections that previously eluded them.

Figure 1. Sequence of Events for Each Trial

(A) The “Compound” prompt was presented for 0.5 s, then persisted for a variable amount of additional time (0–2 s) until a cue from the scanner indicated the beginning of a new whole brain acquisition. (B) A three-word problem appeared in the center of the screen and persisted until subjects indicated with a bimanual button press that they had solved the problem, or until the 30-s time limit elapsed. Thus, event timing and condition were completely dependent on subjects' responses. (C) Following the button press or time limit, subjects were prompted to verbalize the solution (or press the buttons and say “Don't know” if the time limit expired prior to solution) then (D) prompted to indicate (with a bimanual button press) whether they felt insight, as described prior to the experiment. (E) Next, subjects performed 9 s of an unrelated filler task (three line-matching trials, 3 s each), allowing BOLD signal to return to baseline (in areas not involved in line matching).

Figure 2. FMRI Insight Effect in RH aSTG

(A) Voxels showing greater FMRI signal for insight than noninsight solutions, overlaid on the averaged normalized structural image of all subjects. The active area has a volume of 531 mm³ (peak t = 4.89 at 44, −9, −9 in Talairach space). (B) and (C) Group average signal change following the solution event, for insight (red line) and noninsight (blue line) solutions (yellow arrow indicates button press): (B) over entire LH aSTG region; (C) over entire RH aSTG region. (D) Insight solution signal change minus noninsight solution signal change, in RH aSTG (error bars show the standard error of the mean of the difference at each timepoint).

Figure 3. FMRI Signal in RH aSTG during Initial Solving Efforts

(A) Voxels in right temporal lobe showing baseline-to-peak event-related FMRI signal when subjects first encounter problems, overlaid on the averaged normalized structural image of all subjects. The cluster is in RH aSTG, with a volume of 469 mm³, with peak t value of 4.37 at 41, −6, −12 in Talairach space, clearly overlapping with the cluster showing an insight effect at solution. (B) Group average signal change following problem onset (time = 0), for the cluster defined by signal at the problem onset (green line) and the cluster (illustrated in Figure 2A) showing the insight effect at solution (white line). Error bars show the standard error of the mean of the difference at each time point.

Figure 4. Gamma-Band Power for Insight and Noninsight Solutions

(A) Grand average time course of EEG power (in v²) at 39 Hz estimated with the Morlet wavelet transform at right superior temporal electrode T8. The x-axis represents time (in seconds) with the yellow arrow and R marking the point in time of the solution button-press response (i.e., 0.0 s). The green horizontal bars above the x-axis represent the time intervals used in the statistical analyses and topographic maps. Note that gamma-band power for insight trials (red line) starts to increase above power on noninsight trials (blue line) by approximately 0.3 s before the button press. (B) Time-frequency plots of the insight minus noninsight difference shown in (A). The y-axis represents frequency (in Hz); the x-axis represents time (in seconds, with respect to the button press, exactly as shown in [A]). Red areas of the plot reflect times and frequencies at which insight EEG power is greater than noninsight EEG power; blue areas reflect times and frequencies at which noninsight EEG power is greater than insight EEG power. Note the sudden emergence of increased gamma power for insight solutions approximately 0.3 s before the button press. (C) Insight minus noninsight gamma-band differences plotted as topographic maps (LH and RH) of scalp current density (in v²/m²) estimated by a spline-based Laplacian transform computed with a realistic FMRI-derived head model. The Laplacian transform acts as a high-pass spatial filter that minimizes the contribution of activity distant from each electrode, thereby manifesting discrete, relatively superficial sources. The maps are thresholded to show foci of current density at the upper and lower 20% of the scale. Note the prominent effect of insight (effect for insight greater than effect for noninsight, in red) at the right superior temporal electrode (T8) and surrounding electrodes present from −0.30 to −0.02 s (measured with respect to the solution response) that is not present in the earlier epoch (−1.52 to −0.36 s). The blue area over left inferior parietal cortex (electrode P7) indicates that noninsight gamma power is nonsignificantly greater than insight power (F[1,19] < 1) over this region.

Figure 5. Alpha-Band Power for Insight and Noninsight Solutions

(Same conventions as in Figure 4). (A) Time course of EEG power at 9.8 Hz (in v²) at right parietal-occipital electrode (PO8). The x-axis represents time (in seconds), with the green horizontal bars above the x-axis representing the time intervals used in the statistical analyses and topographic maps. The yellow arrow and R (at 0.0 s) signify the time of the button-press response. (B) Time-frequency plots of the insight minus noninsight difference shown in (A). (C) Insight minus noninsight alpha-band differences plotted as topographic maps of scalp current density (in v²/m²). Note that alpha-band power is significantly greater for insight solutions than noninsight solutions during the −1.31 to −0.56 s interval, but not during the preceding (−2.06 to −1.56 s) or subsequent (−0.31 to +0.06 s) intervals. This alpha burst was embedded in a slow decrease in alpha (see [A]), probably reflecting a general increase in cortical activity as effort increases during the course of problem solving.

Figure 6. The Time Course of the Insight Effect

Alpha power (9.8 Hz at right parietal-occipital electrode PO8) and gamma power (39 Hz at right temporal electrode T8) for the insight effect (i.e., correct insight solutions minus correct noninsight solutions, in v²). The left y-axis shows the magnitude of the alpha insight effect (purple line); the right y-axis applies to the gamma insight effect (green line). The x-axis represents time (in seconds). The yellow arrow and R (at 0.0 s) signify the time of the button-press response. Note the transient enhancement of alpha on insight trials (relative to noninsight trials) prior to the gamma burst.