Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1654. Min Range: -9.1654
Max Act: 9.1654. Min Act: -0.1700
Data Index: 1730057 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1654. Min Range: -9.1654
Max Act: 9.1029. Min Act: -0.1700
Data Index: 4898973 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.9154. Min Act: -0.1700
Data Index: 4667132 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.7904. Min Act: -0.1700
Data Index: 1765723 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.7279. Min Act: -0.1700
Data Index: 5310051 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.7279. Min Act: -0.1700
Data Index: 43848 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.7279. Min Act: -0.1700
Data Index: 3391626 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.6654. Min Act: -0.1700
Data Index: 7390810 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.6029. Min Act: -0.1700
Data Index: 5677663 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.6654. Min Act: -0.1700
Data Index: 8622620 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.6029. Min Act: -0.1700
Data Index: 7401436 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.5404. Min Act: -0.1700
Data Index: 4205267 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.5404. Min Act: -0.1700
Data Index: 8116534 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.6029. Min Act: -0.1700
Data Index: 1259808 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.4779. Min Act: -0.1700
Data Index: 3407008 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.5404. Min Act: -0.1700
Data Index: 7584209 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.5404. Min Act: -0.1700
Data Index: 7494829 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.4779. Min Act: -0.1700
Data Index: 2959281 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.4779. Min Act: -0.1700
Data Index: 4788499 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1654. Min Range: -9.1654
Max Act: 8.4779. Min Act: -0.1700
Data Index: 4889056 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19