Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5057 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.9072. Min Act: -0.1700
Data Index: 8694456 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.8447. Min Act: -0.1700
Data Index: 5821884 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.7510. Min Act: -0.1700
Data Index: 4080502 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.7510. Min Act: -0.1700
Data Index: 6739022 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.7510. Min Act: -0.1700
Data Index: 6204743 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.7510. Min Act: -0.1700
Data Index: 5821851 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.6885. Min Act: -0.1700
Data Index: 5821903 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.7197. Min Act: -0.1700
Data Index: 5821870 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.6572. Min Act: -0.1700
Data Index: 5162735 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.6885. Min Act: -0.1700
Data Index: 641359 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.6260. Min Act: -0.1700
Data Index: 2328536 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.6260. Min Act: -0.1700
Data Index: 1886537 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.6260. Min Act: -0.1700
Data Index: 3868750 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.6260. Min Act: -0.1700
Data Index: 3868783 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.6260. Min Act: -0.1700
Data Index: 7095252 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.5947. Min Act: -0.1700
Data Index: 95823 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.5947. Min Act: -0.1700
Data Index: 245890 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.5947. Min Act: -0.1700
Data Index: 8297505 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.6260. Min Act: -0.1700
Data Index: 5584702 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9072. Min Range: -4.9072
Max Act: 4.5947. Min Act: -0.1700
Data Index: 8413944 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19