Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 695 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.4885. Min Act: -0.1693
Data Index: 194621 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.4885. Min Act: -0.1700
Data Index: 3161158 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.4885. Min Act: -0.1700
Data Index: 6720134 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.4260. Min Act: -0.1700
Data Index: 8566139 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.4260. Min Act: -0.1700
Data Index: 5357007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.4573. Min Act: -0.1700
Data Index: 8222943 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.4260. Min Act: -0.1700
Data Index: 3724625 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.4260. Min Act: -0.1700
Data Index: 5442473 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.4260. Min Act: -0.1700
Data Index: 8130964 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.4573. Min Act: -0.1700
Data Index: 1118115 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.3948. Min Act: -0.1700
Data Index: 6394940 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.3948. Min Act: -0.1699
Data Index: 4635338 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.3635. Min Act: -0.1700
Data Index: 7025414 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.3635. Min Act: -0.1700
Data Index: 2586077 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.3323. Min Act: -0.1700
Data Index: 4108009 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.3635. Min Act: -0.1699
Data Index: 5059015 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.3323. Min Act: -0.1700
Data Index: 2316683 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.3323. Min Act: -0.1699
Data Index: 1093661 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.3323. Min Act: -0.1700
Data Index: 198475 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4885. Min Range: -5.4885
Max Act: 5.3323. Min Act: -0.1700
Data Index: 3825983 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19