Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4094 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8395. Min Range: -7.8395
Max Act: 7.8395. Min Act: -0.1700
Data Index: 7443503 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8395. Min Range: -7.8395
Max Act: 7.8083. Min Act: -0.1700
Data Index: 6406014 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8395. Min Range: -7.8395
Max Act: 7.5583. Min Act: -0.1700
Data Index: 8293507 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8395. Min Range: -7.8395
Max Act: 7.3708. Min Act: -0.1700
Data Index: 6627705 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8395. Min Range: -7.8395
Max Act: 7.2770. Min Act: -0.1700
Data Index: 5451967 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8395. Min Range: -7.8395
Max Act: 7.0583. Min Act: -0.1700
Data Index: 3515225 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8395. Min Range: -7.8395
Max Act: 7.0270. Min Act: -0.1700
Data Index: 8085721 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.9958. Min Act: -0.1700
Data Index: 352024 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.9645. Min Act: -0.1700
Data Index: 1219626 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.8395. Min Act: -0.1700
Data Index: 2903537 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.8395. Min Act: -0.1700
Data Index: 5451969 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.8083. Min Act: -0.1700
Data Index: 6215135 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.8083. Min Act: -0.1700
Data Index: 6962975 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.7458. Min Act: -0.1700
Data Index: 5863885 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.6208. Min Act: -0.1700
Data Index: 1963368 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.6520. Min Act: -0.1700
Data Index: 6986523 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.6208. Min Act: -0.1700
Data Index: 5201298 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.5895. Min Act: -0.1700
Data Index: 1550973 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.5895. Min Act: -0.1700
Data Index: 5384971 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8395. Min Range: -7.8395
Max Act: 6.5270. Min Act: -0.1700
Data Index: 2303329 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19