Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 121 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6725. Min Act: -0.1700
Data Index: 6518074 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6412. Min Act: -0.1700
Data Index: 344858 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5475. Min Act: -0.1700
Data Index: 8038880 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5475. Min Act: -0.1700
Data Index: 2132665 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.4537. Min Act: -0.1700
Data Index: 2077036 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.4537. Min Act: -0.1700
Data Index: 4624555 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.4537. Min Act: -0.1700
Data Index: 4990201 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.4225. Min Act: -0.1700
Data Index: 680620 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3912. Min Act: -0.1700
Data Index: 6225048 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3912. Min Act: -0.1700
Data Index: 2946012 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3912. Min Act: -0.1700
Data Index: 5153608 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3912. Min Act: -0.1700
Data Index: 3559257 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3912. Min Act: -0.1700
Data Index: 1255508 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3912. Min Act: -0.1700
Data Index: 5879588 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3600. Min Act: -0.1700
Data Index: 1763491 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3600. Min Act: -0.1700
Data Index: 6859552 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3287. Min Act: -0.1700
Data Index: 461792 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3287. Min Act: -0.1700
Data Index: 2634716 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3287. Min Act: -0.1700
Data Index: 8707452 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3287. Min Act: -0.1700
Data Index: 7469559 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19