Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1945 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.9004. Min Act: -0.1700
Data Index: 4819684 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.7754. Min Act: -0.1700
Data Index: 7476441 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.6504. Min Act: -0.1700
Data Index: 6360979 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.6504. Min Act: -0.1700
Data Index: 7975560 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.5879. Min Act: -0.1700
Data Index: 1052272 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.5254. Min Act: -0.1700
Data Index: 5306996 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.5254. Min Act: -0.1700
Data Index: 3148195 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.5254. Min Act: -0.1700
Data Index: 2323112 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.4004. Min Act: -0.1700
Data Index: 1091068 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.4004. Min Act: -0.1700
Data Index: 2096469 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.4004. Min Act: -0.1700
Data Index: 7812325 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.3379. Min Act: -0.1700
Data Index: 2250881 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.4004. Min Act: -0.1700
Data Index: 8598054 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.4004. Min Act: -0.1700
Data Index: 1664305 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.4004. Min Act: -0.1700
Data Index: 5826882 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.3379. Min Act: -0.1700
Data Index: 4158675 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.3379. Min Act: -0.1700
Data Index: 5664275 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.4004. Min Act: -0.1700
Data Index: 879729 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.3379. Min Act: -0.1700
Data Index: 1138247 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9004. Min Range: -9.9004
Max Act: 9.3379. Min Act: -0.1700
Data Index: 461813 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19