Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.4673. Min Act: -0.1700
Data Index: 357371 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.4673. Min Act: -0.1700
Data Index: 6293041 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.2486. Min Act: -0.1700
Data Index: 6293047 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.2173. Min Act: -0.1700
Data Index: 89767 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.2173. Min Act: -0.1700
Data Index: 5527848 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.1236. Min Act: -0.1700
Data Index: 6314418 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.0923. Min Act: -0.1700
Data Index: 5410586 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.1236. Min Act: -0.1700
Data Index: 8436871 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.0611. Min Act: -0.1700
Data Index: 5112632 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.0611. Min Act: -0.1700
Data Index: 610027 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.0611. Min Act: -0.1700
Data Index: 468058 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.0611. Min Act: -0.1700
Data Index: 8628166 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.0611. Min Act: -0.1700
Data Index: 8742037 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.0298. Min Act: -0.1700
Data Index: 6293042 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.0298. Min Act: -0.1700
Data Index: 2613876 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4673. Min Range: -6.4673
Max Act: 6.0298. Min Act: -0.1700
Data Index: 2427255 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4673. Min Range: -6.4673
Max Act: 5.9986. Min Act: -0.1700
Data Index: 1045550 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4673. Min Range: -6.4673
Max Act: 5.9986. Min Act: -0.1700
Data Index: 4549219 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4673. Min Range: -6.4673
Max Act: 5.9986. Min Act: -0.1700
Data Index: 5814942 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4673. Min Range: -6.4673
Max Act: 5.9673. Min Act: -0.1700
Data Index: 5045151 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19