Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2364 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.5927. Min Act: -0.1700
Data Index: 4019020 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.5302. Min Act: -0.1700
Data Index: 8059264 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.4677. Min Act: -0.1700
Data Index: 4955725 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.3427. Min Act: -0.1700
Data Index: 382736 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.2177. Min Act: -0.1700
Data Index: 5031648 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.1552. Min Act: -0.1700
Data Index: 5352014 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.2177. Min Act: -0.1700
Data Index: 1074828 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.1552. Min Act: -0.1700
Data Index: 1372531 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.2177. Min Act: -0.1700
Data Index: 375662 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.1552. Min Act: -0.1700
Data Index: 7707691 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.1552. Min Act: -0.1700
Data Index: 441368 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.1552. Min Act: -0.1700
Data Index: 8773293 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.0927. Min Act: -0.1700
Data Index: 6782562 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.0927. Min Act: -0.1700
Data Index: 2807504 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.0927. Min Act: -0.1700
Data Index: 4435233 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.0927. Min Act: -0.1700
Data Index: 3919790 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.0302. Min Act: -0.1700
Data Index: 4466912 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.0302. Min Act: -0.1700
Data Index: 32353 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.0302. Min Act: -0.1700
Data Index: 3524087 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5927. Min Range: -9.5927
Max Act: 9.0302. Min Act: -0.1700
Data Index: 2380812 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19