Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6326 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.9921. Min Act: -0.1700
Data Index: 481686 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.7421. Min Act: -0.1700
Data Index: 5544124 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.6171. Min Act: -0.1700
Data Index: 4385432 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.6171. Min Act: -0.1700
Data Index: 936707 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.5546. Min Act: -0.1700
Data Index: 3024518 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.5546. Min Act: -0.1700
Data Index: 1762580 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.5546. Min Act: -0.1700
Data Index: 7696184 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.4296. Min Act: -0.1700
Data Index: 1362474 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.3046. Min Act: -0.1700
Data Index: 3306826 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.2421. Min Act: -0.1700
Data Index: 8539815 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.2421. Min Act: -0.1700
Data Index: 2579771 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.1796. Min Act: -0.1700
Data Index: 3662495 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.1796. Min Act: -0.1700
Data Index: 2557389 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.1171. Min Act: -0.1700
Data Index: 8046462 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.1171. Min Act: -0.1700
Data Index: 6447209 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.0546. Min Act: -0.1700
Data Index: 5306823 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.0546. Min Act: -0.1700
Data Index: 8828820 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.0546. Min Act: -0.1700
Data Index: 6672560 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.0546. Min Act: -0.1700
Data Index: 6837543 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9921. Min Range: -11.9921
Max Act: 11.0546. Min Act: -0.1700
Data Index: 1169565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19