Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.4504. Min Act: -0.1700
Data Index: 5364204 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.3567. Min Act: -0.1700
Data Index: 6651156 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.3879. Min Act: -0.1700
Data Index: 3091899 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2942. Min Act: -0.1700
Data Index: 1775285 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.3254. Min Act: -0.1700
Data Index: 3669826 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2942. Min Act: -0.1700
Data Index: 6355916 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2942. Min Act: -0.1700
Data Index: 1053163 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2942. Min Act: -0.1700
Data Index: 2127676 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2942. Min Act: -0.1700
Data Index: 1859381 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2629. Min Act: -0.1700
Data Index: 223709 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2317. Min Act: -0.1700
Data Index: 6540860 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2317. Min Act: -0.1700
Data Index: 5130413 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2317. Min Act: -0.1700
Data Index: 5507146 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2317. Min Act: -0.1700
Data Index: 4165798 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2629. Min Act: -0.1700
Data Index: 6939952 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2004. Min Act: -0.1700
Data Index: 4955289 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2004. Min Act: -0.1700
Data Index: 2202002 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2004. Min Act: -0.1700
Data Index: 19422 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2004. Min Act: -0.1700
Data Index: 1535391 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4504. Min Range: -5.4504
Max Act: 5.2004. Min Act: -0.1700
Data Index: 5485948 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19