Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4171 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.8103. Min Act: -0.1700
Data Index: 2625784 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.6184. Min Act: -0.1700
Data Index: 1626750 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.6023. Min Act: -0.1700
Data Index: 8705052 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.5701. Min Act: -0.1700
Data Index: 1964020 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.5378. Min Act: -0.1700
Data Index: 6366577 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.5540. Min Act: -0.1700
Data Index: 4949912 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.5540. Min Act: -0.1700
Data Index: 5831880 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.5378. Min Act: -0.1700
Data Index: 2687445 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.4892. Min Act: -0.1700
Data Index: 3120622 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.5054. Min Act: -0.1700
Data Index: 1528212 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.4892. Min Act: -0.1700
Data Index: 6305653 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.4730. Min Act: -0.1700
Data Index: 2563108 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.4730. Min Act: -0.1700
Data Index: 8049935 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.4730. Min Act: -0.1700
Data Index: 5183257 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.4730. Min Act: -0.1700
Data Index: 3257019 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.4892. Min Act: -0.1700
Data Index: 2734833 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.4568. Min Act: -0.1700
Data Index: 2878603 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.4568. Min Act: -0.1700
Data Index: 1251999 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.4405. Min Act: -0.1700
Data Index: 6036882 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8103. Min Range: -2.8103
Max Act: 2.4405. Min Act: -0.1700
Data Index: 3268283 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19