Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4259 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4218. Min Range: -6.4218
Max Act: 6.4218. Min Act: -0.1700
Data Index: 5144875 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4218. Min Range: -6.4218
Max Act: 6.3281. Min Act: -0.1700
Data Index: 8417982 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4218. Min Range: -6.4218
Max Act: 6.2968. Min Act: -0.1700
Data Index: 995348 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4218. Min Range: -6.4218
Max Act: 6.2343. Min Act: -0.1700
Data Index: 4484541 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4218. Min Range: -6.4218
Max Act: 6.1406. Min Act: -0.1700
Data Index: 1810997 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4218. Min Range: -6.4218
Max Act: 6.1718. Min Act: -0.1700
Data Index: 3743214 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4218. Min Range: -6.4218
Max Act: 6.1406. Min Act: -0.1700
Data Index: 227591 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4218. Min Range: -6.4218
Max Act: 6.0468. Min Act: -0.1700
Data Index: 8675322 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4218. Min Range: -6.4218
Max Act: 6.0156. Min Act: -0.1700
Data Index: 3492801 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4218. Min Range: -6.4218
Max Act: 6.0468. Min Act: -0.1700
Data Index: 565291 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4218. Min Range: -6.4218
Max Act: 6.0156. Min Act: -0.1700
Data Index: 6190752 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4218. Min Range: -6.4218
Max Act: 5.9531. Min Act: -0.1700
Data Index: 4603576 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4218. Min Range: -6.4218
Max Act: 5.9843. Min Act: -0.1700
Data Index: 2151468 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4218. Min Range: -6.4218
Max Act: 5.9531. Min Act: -0.1700
Data Index: 2620395 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4218. Min Range: -6.4218
Max Act: 5.9218. Min Act: -0.1700
Data Index: 1975529 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4218. Min Range: -6.4218
Max Act: 5.9218. Min Act: -0.1700
Data Index: 3281942 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4218. Min Range: -6.4218
Max Act: 5.9218. Min Act: -0.1700
Data Index: 8303297 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4218. Min Range: -6.4218
Max Act: 5.8906. Min Act: -0.1700
Data Index: 6920152 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4218. Min Range: -6.4218
Max Act: 5.8593. Min Act: -0.1700
Data Index: 1127942 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4218. Min Range: -6.4218
Max Act: 5.8906. Min Act: -0.1700
Data Index: 4112333 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19