Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4742 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1352. Min Range: -9.1352
Max Act: 9.1352. Min Act: -0.1700
Data Index: 1305519 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1352. Min Range: -9.1352
Max Act: 9.0727. Min Act: -0.1700
Data Index: 2105942 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1352. Min Range: -9.1352
Max Act: 9.0102. Min Act: -0.1700
Data Index: 6077247 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1352. Min Range: -9.1352
Max Act: 9.0102. Min Act: -0.1700
Data Index: 1820878 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.9477. Min Act: -0.1700
Data Index: 4654618 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.9477. Min Act: -0.1700
Data Index: 7784470 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.8852. Min Act: -0.1700
Data Index: 5688726 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.8227. Min Act: -0.1700
Data Index: 1137988 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.8227. Min Act: -0.1700
Data Index: 6615727 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.7602. Min Act: -0.1700
Data Index: 3514968 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.8227. Min Act: -0.1700
Data Index: 8765491 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.8227. Min Act: -0.1700
Data Index: 7461002 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.6977. Min Act: -0.1700
Data Index: 8471857 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.6977. Min Act: -0.1700
Data Index: 1783429 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.6977. Min Act: -0.1700
Data Index: 8563577 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.6977. Min Act: -0.1700
Data Index: 4677697 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.7602. Min Act: -0.1700
Data Index: 823075 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.6352. Min Act: -0.1700
Data Index: 7784466 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.6352. Min Act: -0.1700
Data Index: 6609075 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1352. Min Range: -9.1352
Max Act: 8.5727. Min Act: -0.1700
Data Index: 4821984 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19