Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4442 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.5228. Min Act: -0.1700
Data Index: 6833546 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.4603. Min Act: -0.1700
Data Index: 200153 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.4603. Min Act: -0.1700
Data Index: 1199165 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.4603. Min Act: -0.1700
Data Index: 75169 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3978. Min Act: -0.1700
Data Index: 5030286 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3978. Min Act: -0.1700
Data Index: 169778 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3978. Min Act: -0.1700
Data Index: 5926823 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3978. Min Act: -0.1700
Data Index: 6271230 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3978. Min Act: -0.1700
Data Index: 4070889 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3666. Min Act: -0.1700
Data Index: 5612815 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3666. Min Act: -0.1700
Data Index: 6086033 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3353. Min Act: -0.1700
Data Index: 4655505 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3353. Min Act: -0.1700
Data Index: 4251138 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3353. Min Act: -0.1700
Data Index: 3161762 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3353. Min Act: -0.1700
Data Index: 3026614 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3353. Min Act: -0.1700
Data Index: 1194940 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3353. Min Act: -0.1699
Data Index: 1174138 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3353. Min Act: -0.1700
Data Index: 2318305 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3353. Min Act: -0.1700
Data Index: 2147513 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5228. Min Range: -6.5228
Max Act: 6.3041. Min Act: -0.1700
Data Index: 631254 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19