Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2502. Min Range: -8.2502
Max Act: 8.2502. Min Act: -0.1700
Data Index: 2135520 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2502. Min Range: -8.2502
Max Act: 8.2502. Min Act: -0.1700
Data Index: 1635378 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2502. Min Range: -8.2502
Max Act: 8.0627. Min Act: -0.1700
Data Index: 744718 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2502. Min Range: -8.2502
Max Act: 8.0627. Min Act: -0.1700
Data Index: 5327498 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2502. Min Range: -8.2502
Max Act: 8.0627. Min Act: -0.1700
Data Index: 5513758 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.9689. Min Act: -0.1700
Data Index: 8559360 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.9377. Min Act: -0.1700
Data Index: 5677453 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.9064. Min Act: -0.1700
Data Index: 7084761 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.8439. Min Act: -0.1700
Data Index: 8400323 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.8439. Min Act: -0.1700
Data Index: 5671124 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.8439. Min Act: -0.1700
Data Index: 8150236 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.8127. Min Act: -0.1700
Data Index: 5179089 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.8127. Min Act: -0.1700
Data Index: 3281504 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.7814. Min Act: -0.1700
Data Index: 4763278 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.7189. Min Act: -0.1700
Data Index: 1139889 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.7189. Min Act: -0.1700
Data Index: 8476379 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.7502. Min Act: -0.1700
Data Index: 1749093 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.7502. Min Act: -0.1700
Data Index: 2590974 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.6877. Min Act: -0.1700
Data Index: 7978039 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2502. Min Range: -8.2502
Max Act: 7.6877. Min Act: -0.1700
Data Index: 5971861 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19