Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1896 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.6299. Min Act: -0.1700
Data Index: 8411199 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.6299. Min Act: -0.1700
Data Index: 1376931 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.5361. Min Act: -0.1700
Data Index: 3773629 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.4111. Min Act: -0.1700
Data Index: 7789927 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.3486. Min Act: -0.1700
Data Index: 5686438 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.3486. Min Act: -0.1700
Data Index: 493482 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.3486. Min Act: -0.1700
Data Index: 4863887 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.2549. Min Act: -0.1700
Data Index: 3983274 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.2549. Min Act: -0.1700
Data Index: 6019896 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.2549. Min Act: -0.1700
Data Index: 5205357 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.2236. Min Act: -0.1700
Data Index: 4462103 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.2236. Min Act: -0.1700
Data Index: 5531214 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.1924. Min Act: -0.1700
Data Index: 1493619 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.2236. Min Act: -0.1700
Data Index: 8695047 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.1924. Min Act: -0.1700
Data Index: 6324574 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.1611. Min Act: -0.1700
Data Index: 5480849 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.1611. Min Act: -0.1700
Data Index: 6075169 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.1611. Min Act: -0.1700
Data Index: 5601070 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.1611. Min Act: -0.1700
Data Index: 4763408 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6299. Min Range: -5.6299
Max Act: 5.1611. Min Act: -0.1700
Data Index: 67605 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19