Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4241 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3223. Min Range: -8.3223
Max Act: 8.3223. Min Act: -0.1700
Data Index: 6695965 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3223. Min Range: -8.3223
Max Act: 8.0723. Min Act: -0.1700
Data Index: 4109266 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3223. Min Range: -8.3223
Max Act: 8.0410. Min Act: -0.1700
Data Index: 215780 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.9785. Min Act: -0.1700
Data Index: 8481637 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3223. Min Range: -8.3223
Max Act: 8.0098. Min Act: -0.1700
Data Index: 2260783 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.9785. Min Act: -0.1700
Data Index: 991140 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.8848. Min Act: -0.1700
Data Index: 5229643 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.8848. Min Act: -0.1700
Data Index: 8244789 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.8535. Min Act: -0.1700
Data Index: 5551233 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.7910. Min Act: -0.1700
Data Index: 261893 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.7910. Min Act: -0.1700
Data Index: 1526517 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.7285. Min Act: -0.1700
Data Index: 6106954 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.6973. Min Act: -0.1700
Data Index: 6478562 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.6660. Min Act: -0.1700
Data Index: 2789245 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.7285. Min Act: -0.1700
Data Index: 3895304 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.6973. Min Act: -0.1700
Data Index: 5375947 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.6660. Min Act: -0.1700
Data Index: 8159729 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.6348. Min Act: -0.1700
Data Index: 6746643 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.6035. Min Act: -0.1700
Data Index: 4933504 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3223. Min Range: -8.3223
Max Act: 7.6035. Min Act: -0.1700
Data Index: 7221273 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19