Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 194 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6320. Min Range: -6.6320
Max Act: 6.6320. Min Act: -0.1700
Data Index: 2939893 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.8195. Min Act: -0.1700
Data Index: 125316 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.7883. Min Act: -0.1700
Data Index: 8118894 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.7570. Min Act: -0.1700
Data Index: 7020246 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.6945. Min Act: -0.1700
Data Index: 4537689 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.6945. Min Act: -0.1700
Data Index: 8105149 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.6320. Min Act: -0.1700
Data Index: 5619771 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.6320. Min Act: -0.1700
Data Index: 7020244 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.6320. Min Act: -0.1700
Data Index: 3006390 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.5695. Min Act: -0.1700
Data Index: 4859732 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.5695. Min Act: -0.1700
Data Index: 1988947 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.5695. Min Act: -0.1700
Data Index: 2122928 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.5383. Min Act: -0.1700
Data Index: 3445125 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.5383. Min Act: -0.1700
Data Index: 8344147 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.5383. Min Act: -0.1700
Data Index: 3020384 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.5383. Min Act: -0.1700
Data Index: 1317357 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.5383. Min Act: -0.1700
Data Index: 7770349 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.5070. Min Act: -0.1700
Data Index: 7638369 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.4758. Min Act: -0.1700
Data Index: 3776317 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6320. Min Range: -6.6320
Max Act: 5.4758. Min Act: -0.1700
Data Index: 3037899 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19