Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3762 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.9867. Min Act: -0.1700
Data Index: 7582439 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.9555. Min Act: -0.1700
Data Index: 3379025 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.9242. Min Act: -0.1700
Data Index: 6175296 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.8305. Min Act: -0.1700
Data Index: 3201287 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.7680. Min Act: -0.1700
Data Index: 983153 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.7367. Min Act: -0.1700
Data Index: 555961 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.7367. Min Act: -0.1700
Data Index: 4318476 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.7367. Min Act: -0.1700
Data Index: 4919966 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.7055. Min Act: -0.1700
Data Index: 3506523 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.7055. Min Act: -0.1700
Data Index: 1685315 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.7055. Min Act: -0.1700
Data Index: 1870098 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6430. Min Act: -0.1700
Data Index: 3805519 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6742. Min Act: -0.1700
Data Index: 3670606 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6742. Min Act: -0.1700
Data Index: 3116969 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6742. Min Act: -0.1700
Data Index: 4919843 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6742. Min Act: -0.1700
Data Index: 8045363 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6430. Min Act: -0.1700
Data Index: 3567144 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6430. Min Act: -0.1700
Data Index: 4806217 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6117. Min Act: -0.1700
Data Index: 3762423 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6430. Min Act: -0.1700
Data Index: 2709401 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19