Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1008. Min Range: -3.1008
Max Act: 3.1008. Min Act: -0.1700
Data Index: 3215428 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1008. Min Range: -3.1008
Max Act: 3.0062. Min Act: -0.1700
Data Index: 1507365 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.9587. Min Act: -0.1700
Data Index: 4349827 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.9271. Min Act: -0.1700
Data Index: 8011311 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.9271. Min Act: -0.1700
Data Index: 1563761 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8954. Min Act: -0.1700
Data Index: 1545648 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8954. Min Act: -0.1700
Data Index: 8405599 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8477. Min Act: -0.1700
Data Index: 3768768 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8477. Min Act: -0.1700
Data Index: 6117765 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8318. Min Act: -0.1700
Data Index: 385697 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8477. Min Act: -0.1700
Data Index: 2098285 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8318. Min Act: -0.1700
Data Index: 885753 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8318. Min Act: -0.1700
Data Index: 4659226 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8159. Min Act: -0.1700
Data Index: 4549942 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8159. Min Act: -0.1700
Data Index: 4423604 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8159. Min Act: -0.1700
Data Index: 7501297 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8000. Min Act: -0.1700
Data Index: 8139694 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.7841. Min Act: -0.1700
Data Index: 2021264 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8000. Min Act: -0.1700
Data Index: 1900933 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1008. Min Range: -3.1008
Max Act: 2.8159. Min Act: -0.1700
Data Index: 4333690 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19