Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5178 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.8103. Min Act: -0.1700
Data Index: 1126656 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.8103. Min Act: -0.1700
Data Index: 4692504 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.7166. Min Act: -0.1700
Data Index: 5850375 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.7166. Min Act: -0.1700
Data Index: 968438 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.6541. Min Act: -0.1700
Data Index: 3433361 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.6541. Min Act: -0.1700
Data Index: 2398933 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.6541. Min Act: -0.1700
Data Index: 1974805 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.6228. Min Act: -0.1700
Data Index: 2222512 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.6228. Min Act: -0.1700
Data Index: 1007890 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.6228. Min Act: -0.1700
Data Index: 306241 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.5916. Min Act: -0.1700
Data Index: 2901322 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.5916. Min Act: -0.1700
Data Index: 5526487 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.5916. Min Act: -0.1700
Data Index: 8505006 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.5603. Min Act: -0.1700
Data Index: 7622868 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.5603. Min Act: -0.1700
Data Index: 563440 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.5291. Min Act: -0.1700
Data Index: 915715 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.4978. Min Act: -0.1700
Data Index: 8681712 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.5291. Min Act: -0.1700
Data Index: 475319 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.4978. Min Act: -0.1700
Data Index: 6820468 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8103. Min Range: -5.8103
Max Act: 5.4978. Min Act: -0.1700
Data Index: 58527 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19