Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4163 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.7211. Min Act: -0.1700
Data Index: 435369 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.5336. Min Act: -0.1700
Data Index: 4754560 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.4399. Min Act: -0.1700
Data Index: 6310599 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.5024. Min Act: -0.1700
Data Index: 7256070 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.4399. Min Act: -0.1700
Data Index: 7662657 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.4086. Min Act: -0.1700
Data Index: 3664189 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.4086. Min Act: -0.1700
Data Index: 7709471 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.4086. Min Act: -0.1700
Data Index: 5125533 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.4399. Min Act: -0.1700
Data Index: 6266765 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.3461. Min Act: -0.1700
Data Index: 1247338 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.3149. Min Act: -0.1700
Data Index: 6005410 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.3461. Min Act: -0.1700
Data Index: 6486222 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.3461. Min Act: -0.1700
Data Index: 7630058 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.3461. Min Act: -0.1700
Data Index: 4097398 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.3461. Min Act: -0.1700
Data Index: 3562043 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.3149. Min Act: -0.1700
Data Index: 4306687 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.3149. Min Act: -0.1700
Data Index: 5561967 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.3149. Min Act: -0.1700
Data Index: 3990435 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.3149. Min Act: -0.1700
Data Index: 6688353 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7211. Min Range: -7.7211
Max Act: 7.3149. Min Act: -0.1700
Data Index: 3717793 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19