Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5083 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3383. Min Range: -12.3383
Max Act: 12.3383. Min Act: -0.1700
Data Index: 894585 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.9008. Min Act: -0.1700
Data Index: 7183034 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.4008. Min Act: -0.1700
Data Index: 2139019 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.3383. Min Act: -0.1700
Data Index: 110714 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.3383. Min Act: -0.1700
Data Index: 1416726 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.2133. Min Act: -0.1700
Data Index: 8718482 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.2133. Min Act: -0.1700
Data Index: 5987835 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.1508. Min Act: -0.1700
Data Index: 6999171 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.1508. Min Act: -0.1700
Data Index: 6286724 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.1508. Min Act: -0.1700
Data Index: 4168866 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.1508. Min Act: -0.1700
Data Index: 2580656 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.0883. Min Act: -0.1700
Data Index: 869028 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.0883. Min Act: -0.1700
Data Index: 8054007 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.0258. Min Act: -0.1700
Data Index: 22229 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.0258. Min Act: -0.1700
Data Index: 1416727 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3383. Min Range: -12.3383
Max Act: 11.0258. Min Act: -0.1700
Data Index: 8301369 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3383. Min Range: -12.3383
Max Act: 10.9633. Min Act: -0.1700
Data Index: 4696911 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3383. Min Range: -12.3383
Max Act: 10.9633. Min Act: -0.1700
Data Index: 7050337 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3383. Min Range: -12.3383
Max Act: 10.9633. Min Act: -0.1700
Data Index: 2277270 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3383. Min Range: -12.3383
Max Act: 10.9633. Min Act: -0.1700
Data Index: 999395 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19