Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4808 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.9723. Min Act: -0.1700
Data Index: 4152064 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.8473. Min Act: -0.1700
Data Index: 7485385 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.8160. Min Act: -0.1700
Data Index: 618417 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.6598. Min Act: -0.1700
Data Index: 1436950 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.5348. Min Act: -0.1700
Data Index: 4745210 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.5035. Min Act: -0.1700
Data Index: 8202129 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.4098. Min Act: -0.1700
Data Index: 4811183 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.3785. Min Act: -0.1700
Data Index: 4566336 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.3785. Min Act: -0.1700
Data Index: 667804 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.3473. Min Act: -0.1700
Data Index: 4285007 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.3473. Min Act: -0.1700
Data Index: 5610 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.2848. Min Act: -0.1700
Data Index: 4681354 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.2848. Min Act: -0.1700
Data Index: 2408916 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.2223. Min Act: -0.1700
Data Index: 5056735 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.2535. Min Act: -0.1700
Data Index: 313107 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.2223. Min Act: -0.1700
Data Index: 4460108 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.1910. Min Act: -0.1700
Data Index: 7111375 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.2223. Min Act: -0.1700
Data Index: 3451994 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.1910. Min Act: -0.1700
Data Index: 980537 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9723. Min Range: -5.9723
Max Act: 5.1598. Min Act: -0.1700
Data Index: 7670510 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19