Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 536 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.7526. Min Act: -0.1700
Data Index: 2321977 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.6589. Min Act: -0.1700
Data Index: 2759073 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.5651. Min Act: -0.1700
Data Index: 5055153 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.4089. Min Act: -0.1700
Data Index: 7239279 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.3776. Min Act: -0.1700
Data Index: 3542083 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.2214. Min Act: -0.1700
Data Index: 5055156 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.2214. Min Act: -0.1700
Data Index: 1213130 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.2214. Min Act: -0.1700
Data Index: 6888721 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.2214. Min Act: -0.1700
Data Index: 5867676 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.1589. Min Act: -0.1700
Data Index: 2321975 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.1589. Min Act: -0.1700
Data Index: 6937713 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.1901. Min Act: -0.1700
Data Index: 1857120 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.1901. Min Act: -0.1700
Data Index: 5288215 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.0964. Min Act: -0.1700
Data Index: 7497651 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.1276. Min Act: -0.1700
Data Index: 7920724 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.0964. Min Act: -0.1700
Data Index: 3473443 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.1276. Min Act: -0.1700
Data Index: 227949 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7526. Min Range: -6.7526
Max Act: 5.8151. Min Act: -0.1700
Data Index: 6214464 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.1276. Min Act: -0.1700
Data Index: 7239278 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7526. Min Range: -6.7526
Max Act: 6.0964. Min Act: -0.1700
Data Index: 6410884 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19