Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 393 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4379. Min Range: -3.4379
Max Act: 3.4379. Min Act: -0.1700
Data Index: 5932143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4379. Min Range: -3.4379
Max Act: 3.2654. Min Act: -0.1700
Data Index: 6767198 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4379. Min Range: -3.4379
Max Act: 3.0765. Min Act: -0.1700
Data Index: 4693618 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4379. Min Range: -3.4379
Max Act: 3.0765. Min Act: -0.1700
Data Index: 611450 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4379. Min Range: -3.4379
Max Act: 3.0292. Min Act: -0.1700
Data Index: 4974135 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4379. Min Range: -3.4379
Max Act: 3.0134. Min Act: -0.1700
Data Index: 3235264 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4379. Min Range: -3.4379
Max Act: 3.0134. Min Act: -0.1700
Data Index: 797649 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.9976. Min Act: -0.1700
Data Index: 7032742 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.9976. Min Act: -0.1700
Data Index: 1417801 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.9818. Min Act: -0.1700
Data Index: 6664188 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.9660. Min Act: -0.1700
Data Index: 8802989 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.9501. Min Act: -0.1700
Data Index: 7904657 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.9185. Min Act: -0.1700
Data Index: 1267026 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.9185. Min Act: -0.1700
Data Index: 4233675 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.8868. Min Act: -0.1700
Data Index: 8597589 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.8868. Min Act: -0.1700
Data Index: 7073979 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.9026. Min Act: -0.1700
Data Index: 4359210 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.8868. Min Act: -0.1700
Data Index: 8257936 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.8709. Min Act: -0.1700
Data Index: 3001285 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4379. Min Range: -3.4379
Max Act: 2.8709. Min Act: -0.1700
Data Index: 2550389 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19