Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8810. Min Act: -0.1700
Data Index: 335004 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8497. Min Act: -0.1700
Data Index: 7157133 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8497. Min Act: -0.1700
Data Index: 125415 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8185. Min Act: -0.1700
Data Index: 3940865 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.7872. Min Act: -0.1700
Data Index: 5855945 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8497. Min Act: -0.1700
Data Index: 7947846 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8185. Min Act: -0.1700
Data Index: 1921585 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8185. Min Act: -0.1700
Data Index: 8091088 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8185. Min Act: -0.1700
Data Index: 5506439 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8497. Min Act: -0.1700
Data Index: 5959582 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8185. Min Act: -0.1700
Data Index: 5699248 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8497. Min Act: -0.1700
Data Index: 3010886 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.7872. Min Act: -0.1700
Data Index: 7512252 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.7872. Min Act: -0.1700
Data Index: 6662318 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.7872. Min Act: -0.1700
Data Index: 8699019 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.8185. Min Act: -0.1700
Data Index: 4611014 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.7872. Min Act: -0.1700
Data Index: 3501246 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.7559. Min Act: -0.1700
Data Index: 2094079 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.7559. Min Act: -0.1700
Data Index: 6652238 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8810. Min Range: -3.8810
Max Act: 3.7559. Min Act: -0.1700
Data Index: 2780206 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19