Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3623 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6227. Min Range: -6.6227
Max Act: 6.6227. Min Act: -0.1700
Data Index: 3977934 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6227. Min Range: -6.6227
Max Act: 6.4039. Min Act: -0.1700
Data Index: 16727 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6227. Min Range: -6.6227
Max Act: 6.2164. Min Act: -0.1700
Data Index: 2803003 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6227. Min Range: -6.6227
Max Act: 6.2164. Min Act: -0.1700
Data Index: 4232038 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6227. Min Range: -6.6227
Max Act: 6.1539. Min Act: -0.1700
Data Index: 7677641 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6227. Min Range: -6.6227
Max Act: 6.0289. Min Act: -0.1700
Data Index: 6804792 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.9664. Min Act: -0.1700
Data Index: 5120416 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.9352. Min Act: -0.1700
Data Index: 2396788 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.9352. Min Act: -0.1700
Data Index: 8436450 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.9352. Min Act: -0.1700
Data Index: 7487041 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.9352. Min Act: -0.1700
Data Index: 403555 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.9352. Min Act: -0.1700
Data Index: 2479283 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.9039. Min Act: -0.1700
Data Index: 4508142 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.8727. Min Act: -0.1700
Data Index: 6276878 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.9039. Min Act: -0.1700
Data Index: 6031694 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.8727. Min Act: -0.1700
Data Index: 8212888 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4568177 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.8414. Min Act: -0.1700
Data Index: 4973794 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.8102. Min Act: -0.1700
Data Index: 1004002 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6227. Min Range: -6.6227
Max Act: 5.8102. Min Act: -0.1700
Data Index: 342137 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19