Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 624 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.5924. Min Act: -0.1700
Data Index: 6513996 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.3736. Min Act: -0.1700
Data Index: 7601738 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.2799. Min Act: -0.1700
Data Index: 4873091 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.1861. Min Act: -0.1700
Data Index: 7306265 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.1861. Min Act: -0.1700
Data Index: 8386013 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.1549. Min Act: -0.1700
Data Index: 7030844 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.1549. Min Act: -0.1700
Data Index: 6620106 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.0923. Min Act: -0.1700
Data Index: 5271014 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.1236. Min Act: -0.1700
Data Index: 3169427 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.0923. Min Act: -0.1700
Data Index: 704448 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.0611. Min Act: -0.1700
Data Index: 3564187 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.0611. Min Act: -0.1700
Data Index: 7874044 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.0298. Min Act: -0.1700
Data Index: 154111 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5924. Min Range: -4.5924
Max Act: 3.9986. Min Act: -0.1700
Data Index: 7862778 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.0298. Min Act: -0.1700
Data Index: 7264717 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.0298. Min Act: -0.1700
Data Index: 2189697 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5924. Min Range: -4.5924
Max Act: 3.9673. Min Act: -0.1700
Data Index: 7367596 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5924. Min Range: -4.5924
Max Act: 3.9673. Min Act: -0.1700
Data Index: 5363243 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5924. Min Range: -4.5924
Max Act: 3.9673. Min Act: -0.1700
Data Index: 6069692 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5924. Min Range: -4.5924
Max Act: 4.0298. Min Act: -0.1700
Data Index: 7205584 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19