Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1574 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1342. Min Range: -6.1342
Max Act: 6.1342. Min Act: -0.1700
Data Index: 3501520 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1342. Min Range: -6.1342
Max Act: 6.0717. Min Act: -0.1700
Data Index: 1762999 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1342. Min Range: -6.1342
Max Act: 6.0405. Min Act: -0.1700
Data Index: 6318285 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.9780. Min Act: -0.1700
Data Index: 5332420 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.9780. Min Act: -0.1700
Data Index: 6484350 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.9155. Min Act: -0.1700
Data Index: 2340391 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.8842. Min Act: -0.1700
Data Index: 5824442 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.8842. Min Act: -0.1700
Data Index: 2042146 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.8217. Min Act: -0.1700
Data Index: 373697 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.8842. Min Act: -0.1700
Data Index: 3483854 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.8530. Min Act: -0.1700
Data Index: 5824568 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.8217. Min Act: -0.1700
Data Index: 4508746 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.8217. Min Act: -0.1700
Data Index: 58082 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.7905. Min Act: -0.1700
Data Index: 1489643 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.7905. Min Act: -0.1700
Data Index: 6789601 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.7592. Min Act: -0.1700
Data Index: 8162337 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.7592. Min Act: -0.1700
Data Index: 7217495 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.7592. Min Act: -0.1700
Data Index: 2533358 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.7905. Min Act: -0.1700
Data Index: 1439661 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1342. Min Range: -6.1342
Max Act: 5.7592. Min Act: -0.1700
Data Index: 6945063 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19