Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2749 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.6068. Min Act: -0.1700
Data Index: 34905 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.3255. Min Act: -0.1700
Data Index: 1638575 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.2005. Min Act: -0.1700
Data Index: 5207506 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.2318. Min Act: -0.1700
Data Index: 8556117 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.2318. Min Act: -0.1700
Data Index: 4172651 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.2005. Min Act: -0.1700
Data Index: 5524026 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.1693. Min Act: -0.1700
Data Index: 6559903 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.1693. Min Act: -0.1700
Data Index: 5300062 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.1693. Min Act: -0.1700
Data Index: 2943136 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.1380. Min Act: -0.1700
Data Index: 7177123 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.1380. Min Act: -0.1700
Data Index: 4484805 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.1068. Min Act: -0.1700
Data Index: 2373354 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.1068. Min Act: -0.1700
Data Index: 1001393 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.0443. Min Act: -0.1700
Data Index: 911635 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.0443. Min Act: -0.1700
Data Index: 4803738 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.0443. Min Act: -0.1700
Data Index: 2799494 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.0130. Min Act: -0.1700
Data Index: 2821279 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6068. Min Range: -7.6068
Max Act: 7.0130. Min Act: -0.1700
Data Index: 4037301 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6068. Min Range: -7.6068
Max Act: 6.9818. Min Act: -0.1700
Data Index: 640677 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6068. Min Range: -7.6068
Max Act: 6.9818. Min Act: -0.1700
Data Index: 462288 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19