Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1053 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.8941. Min Act: -0.1700
Data Index: 4955472 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.7066. Min Act: -0.1700
Data Index: 6675665 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.6754. Min Act: -0.1700
Data Index: 2672914 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.6129. Min Act: -0.1700
Data Index: 7507527 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.6129. Min Act: -0.1700
Data Index: 287899 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.5816. Min Act: -0.1700
Data Index: 8414682 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.5816. Min Act: -0.1700
Data Index: 3335885 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.5816. Min Act: -0.1700
Data Index: 5001127 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.5504. Min Act: -0.1700
Data Index: 8101282 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.5504. Min Act: -0.1700
Data Index: 4519220 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.5191. Min Act: -0.1700
Data Index: 6394336 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.5191. Min Act: -0.1700
Data Index: 6578656 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.5191. Min Act: -0.1700
Data Index: 5001133 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.4566. Min Act: -0.1700
Data Index: 8521409 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.4566. Min Act: -0.1700
Data Index: 5112586 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.4566. Min Act: -0.1700
Data Index: 6904796 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.4566. Min Act: -0.1700
Data Index: 3011001 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.4879. Min Act: -0.1700
Data Index: 4428054 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.4254. Min Act: -0.1700
Data Index: 3439941 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8941. Min Range: -5.8941
Max Act: 5.4254. Min Act: -0.1700
Data Index: 8233804 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19