Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3849 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0679. Min Range: -7.0679
Max Act: 7.0679. Min Act: -0.1700
Data Index: 5916647 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0679. Min Range: -7.0679
Max Act: 7.0679. Min Act: -0.1700
Data Index: 33549 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0679. Min Range: -7.0679
Max Act: 7.0679. Min Act: -0.1700
Data Index: 5722579 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.9429. Min Act: -0.1700
Data Index: 2007778 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.9429. Min Act: -0.1700
Data Index: 8592837 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.9117. Min Act: -0.1700
Data Index: 4229392 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.8179. Min Act: -0.1700
Data Index: 4839039 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.8179. Min Act: -0.1700
Data Index: 8598697 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.8179. Min Act: -0.1700
Data Index: 7162468 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.7867. Min Act: -0.1700
Data Index: 2394545 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.7867. Min Act: -0.1700
Data Index: 5215083 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.7242. Min Act: -0.1700
Data Index: 4990844 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.7554. Min Act: -0.1700
Data Index: 4571488 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.7554. Min Act: -0.1700
Data Index: 6182613 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.7554. Min Act: -0.1700
Data Index: 3913275 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.7242. Min Act: -0.1700
Data Index: 3482040 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.7242. Min Act: -0.1700
Data Index: 5846906 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.7554. Min Act: -0.1700
Data Index: 4645215 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.7242. Min Act: -0.1700
Data Index: 8800699 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0679. Min Range: -7.0679
Max Act: 6.6929. Min Act: -0.1700
Data Index: 6975825 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19