Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4782 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.5941. Min Act: -0.1700
Data Index: 2558422 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.5941. Min Act: -0.1700
Data Index: 8485497 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.5315. Min Act: -0.1700
Data Index: 2372559 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.5002. Min Act: -0.1700
Data Index: 4415575 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.4688. Min Act: -0.1700
Data Index: 454393 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.4375. Min Act: -0.1700
Data Index: 5315199 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.4375. Min Act: -0.1700
Data Index: 780721 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.4375. Min Act: -0.1700
Data Index: 1207703 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.4061. Min Act: -0.1700
Data Index: 6494008 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.4061. Min Act: -0.1700
Data Index: 7996352 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.3905. Min Act: -0.1700
Data Index: 4168057 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.4061. Min Act: -0.1700
Data Index: 5975201 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.3905. Min Act: -0.1700
Data Index: 4730387 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.3905. Min Act: -0.1700
Data Index: 3418853 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.3591. Min Act: -0.1700
Data Index: 5169893 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.3434. Min Act: -0.1700
Data Index: 8190226 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.3434. Min Act: -0.1700
Data Index: 3298702 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.3434. Min Act: -0.1700
Data Index: 2446324 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.3434. Min Act: -0.1700
Data Index: 2392599 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5941. Min Range: -3.5941
Max Act: 3.3277. Min Act: -0.1700
Data Index: 261388 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19