Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1971. Min Act: -0.1700
Data Index: 4048496 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1971. Min Act: -0.1700
Data Index: 8353696 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1659. Min Act: -0.1700
Data Index: 5555733 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1346. Min Act: -0.1700
Data Index: 25170 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1346. Min Act: -0.1700
Data Index: 7052482 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1346. Min Act: -0.1700
Data Index: 4003299 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1034. Min Act: -0.1700
Data Index: 245727 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1034. Min Act: -0.1700
Data Index: 4045601 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1034. Min Act: -0.1700
Data Index: 2924014 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1034. Min Act: -0.1700
Data Index: 2713826 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1034. Min Act: -0.1700
Data Index: 7375308 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.1034. Min Act: -0.1700
Data Index: 7827448 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.0721. Min Act: -0.1700
Data Index: 2941326 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.0721. Min Act: -0.1700
Data Index: 2057714 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.0721. Min Act: -0.1700
Data Index: 246930 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.0721. Min Act: -0.1700
Data Index: 3852369 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.0721. Min Act: -0.1700
Data Index: 6621472 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.0409. Min Act: -0.1700
Data Index: 104147 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.0409. Min Act: -0.1700
Data Index: 1515051 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1971. Min Range: -5.1971
Max Act: 5.0409. Min Act: -0.1700
Data Index: 3420552 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19