Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 655 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.8348. Min Act: -0.1700
Data Index: 4669715 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.5223. Min Act: -0.1700
Data Index: 2049534 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.5223. Min Act: -0.1700
Data Index: 2850670 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.3973. Min Act: -0.1700
Data Index: 8782057 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.3973. Min Act: -0.1700
Data Index: 360719 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.3973. Min Act: -0.1700
Data Index: 7922499 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.2723. Min Act: -0.1700
Data Index: 5819992 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.1473. Min Act: -0.1700
Data Index: 3249836 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.2098. Min Act: -0.1700
Data Index: 1339489 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.1473. Min Act: -0.1700
Data Index: 7588902 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.1473. Min Act: -0.1700
Data Index: 4999099 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.0223. Min Act: -0.1700
Data Index: 7960552 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.0848. Min Act: -0.1700
Data Index: 8344044 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8348. Min Range: -9.8348
Max Act: 8.9598. Min Act: -0.1700
Data Index: 3940165 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.0223. Min Act: -0.1700
Data Index: 4002728 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.0223. Min Act: -0.1700
Data Index: 761630 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8348. Min Range: -9.8348
Max Act: 9.0223. Min Act: -0.1700
Data Index: 5578231 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8348. Min Range: -9.8348
Max Act: 8.9598. Min Act: -0.1700
Data Index: 8559967 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8348. Min Range: -9.8348
Max Act: 8.8973. Min Act: -0.1700
Data Index: 71898 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8348. Min Range: -9.8348
Max Act: 8.8973. Min Act: -0.1700
Data Index: 4168173 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19