Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4723 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2163. Min Range: -6.2163
Max Act: 6.2163. Min Act: -0.1700
Data Index: 2712825 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2163. Min Range: -6.2163
Max Act: 6.1851. Min Act: -0.1700
Data Index: 4041766 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2163. Min Range: -6.2163
Max Act: 6.1226. Min Act: -0.1700
Data Index: 1704671 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2163. Min Range: -6.2163
Max Act: 6.1226. Min Act: -0.1700
Data Index: 6059748 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2163. Min Range: -6.2163
Max Act: 6.0913. Min Act: -0.1700
Data Index: 6294454 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2163. Min Range: -6.2163
Max Act: 6.0601. Min Act: -0.1700
Data Index: 8213618 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.9663. Min Act: -0.1700
Data Index: 6362700 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.9663. Min Act: -0.1700
Data Index: 2849989 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.9351. Min Act: -0.1700
Data Index: 6784641 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.9038. Min Act: -0.1700
Data Index: 6200507 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.8726. Min Act: -0.1700
Data Index: 8443779 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.8726. Min Act: -0.1700
Data Index: 6477692 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.8413. Min Act: -0.1700
Data Index: 585425 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.8413. Min Act: -0.1700
Data Index: 659171 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.8726. Min Act: -0.1700
Data Index: 5042835 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.8413. Min Act: -0.1700
Data Index: 1688449 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.8413. Min Act: -0.1700
Data Index: 450795 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.8413. Min Act: -0.1700
Data Index: 4964083 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.8413. Min Act: -0.1700
Data Index: 2784577 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2163. Min Range: -6.2163
Max Act: 5.8101. Min Act: -0.1700
Data Index: 2021191 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19