Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2307 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.9378. Min Act: -0.1700
Data Index: 7815966 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.9378. Min Act: -0.1700
Data Index: 7815971 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.9037. Min Act: -0.1700
Data Index: 7815952 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.8696. Min Act: -0.1700
Data Index: 5620384 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.8353. Min Act: -0.1700
Data Index: 3450000 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7838. Min Act: -0.1700
Data Index: 5779321 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.8182. Min Act: -0.1700
Data Index: 7460265 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.8010. Min Act: -0.1700
Data Index: 5457313 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7838. Min Act: -0.1700
Data Index: 3927511 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7838. Min Act: -0.1700
Data Index: 1774869 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7665. Min Act: -0.1700
Data Index: 2645278 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7838. Min Act: -0.1700
Data Index: 4339659 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7665. Min Act: -0.1700
Data Index: 1727624 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7665. Min Act: -0.1700
Data Index: 4463280 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7665. Min Act: -0.1700
Data Index: 2976048 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7665. Min Act: -0.1700
Data Index: 4463283 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7320. Min Act: -0.1700
Data Index: 5353905 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7493. Min Act: -0.1700
Data Index: 8223829 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7493. Min Act: -0.1700
Data Index: 2645282 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9378. Min Range: -1.9378
Max Act: 1.7493. Min Act: -0.1700
Data Index: 4339658 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19