Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3970 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.7252. Min Act: -0.1700
Data Index: 7957175 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.6939. Min Act: -0.1700
Data Index: 7648329 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.6627. Min Act: -0.1700
Data Index: 533660 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.6002. Min Act: -0.1700
Data Index: 6979442 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.6002. Min Act: -0.1700
Data Index: 7880005 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.5689. Min Act: -0.1700
Data Index: 6792580 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.5377. Min Act: -0.1700
Data Index: 277097 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.5064. Min Act: -0.1700
Data Index: 3617466 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.5064. Min Act: -0.1700
Data Index: 6754538 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.5064. Min Act: -0.1700
Data Index: 1851807 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.4439. Min Act: -0.1700
Data Index: 7603280 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.4439. Min Act: -0.1700
Data Index: 1221347 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.3814. Min Act: -0.1700
Data Index: 7085056 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.3814. Min Act: -0.1700
Data Index: 6769717 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.3502. Min Act: -0.1700
Data Index: 3473748 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.3502. Min Act: -0.1700
Data Index: 6937836 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.3189. Min Act: -0.1700
Data Index: 6599535 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.2877. Min Act: -0.1700
Data Index: 2350774 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.3189. Min Act: -0.1700
Data Index: 6593453 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7252. Min Range: -5.7252
Max Act: 5.3189. Min Act: -0.1700
Data Index: 3350900 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19