Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1069 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.8277. Min Act: -0.1700
Data Index: 4805991 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.8277. Min Act: -0.1700
Data Index: 535904 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.6714. Min Act: -0.1700
Data Index: 1635391 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.6402. Min Act: -0.1700
Data Index: 5395480 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.6089. Min Act: -0.1700
Data Index: 4474296 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.5464. Min Act: -0.1700
Data Index: 603497 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.5464. Min Act: -0.1700
Data Index: 3239479 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.5777. Min Act: -0.1700
Data Index: 368017 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.5464. Min Act: -0.1700
Data Index: 7023867 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.5152. Min Act: -0.1700
Data Index: 856495 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.5152. Min Act: -0.1700
Data Index: 1590650 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.4214. Min Act: -0.1700
Data Index: 5326510 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.4214. Min Act: -0.1700
Data Index: 2646743 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.4214. Min Act: -0.1700
Data Index: 2295029 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.4527. Min Act: -0.1700
Data Index: 1481234 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.3902. Min Act: -0.1700
Data Index: 301689 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.3902. Min Act: -0.1700
Data Index: 3324270 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.3589. Min Act: -0.1700
Data Index: 8284727 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.3902. Min Act: -0.1700
Data Index: 6606448 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8277. Min Range: -4.8277
Max Act: 4.3589. Min Act: -0.1700
Data Index: 3113055 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19