Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 658 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4979. Min Range: -6.4979
Max Act: 6.4979. Min Act: -0.1700
Data Index: 1067090 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.7791. Min Act: -0.1700
Data Index: 2493223 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.8104. Min Act: -0.1700
Data Index: 1118270 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.7166. Min Act: -0.1700
Data Index: 2883805 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.6854. Min Act: -0.1700
Data Index: 224407 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.6854. Min Act: -0.1700
Data Index: 5957621 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.6229. Min Act: -0.1700
Data Index: 1036181 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.5604. Min Act: -0.1700
Data Index: 6752003 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.4979. Min Act: -0.1700
Data Index: 599984 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.4979. Min Act: -0.1700
Data Index: 1883887 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.4666. Min Act: -0.1700
Data Index: 4440334 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.4354. Min Act: -0.1700
Data Index: 7298300 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.4354. Min Act: -0.1700
Data Index: 35060 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.4354. Min Act: -0.1700
Data Index: 1036180 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.4354. Min Act: -0.1700
Data Index: 2043886 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.4354. Min Act: -0.1700
Data Index: 6198343 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.4041. Min Act: -0.1700
Data Index: 3067642 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.4041. Min Act: -0.1700
Data Index: 7772007 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.4041. Min Act: -0.1700
Data Index: 5210509 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4979. Min Range: -6.4979
Max Act: 5.3416. Min Act: -0.1700
Data Index: 1482897 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19