Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4904 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1766. Min Range: -8.1766
Max Act: 8.1766. Min Act: -0.1700
Data Index: 5109878 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1766. Min Range: -8.1766
Max Act: 8.1141. Min Act: -0.1700
Data Index: 5365729 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1766. Min Range: -8.1766
Max Act: 8.0516. Min Act: -0.1700
Data Index: 812017 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.8016. Min Act: -0.1700
Data Index: 3919767 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.7704. Min Act: -0.1700
Data Index: 2783681 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.7704. Min Act: -0.1700
Data Index: 6036409 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.7391. Min Act: -0.1700
Data Index: 4800490 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.7391. Min Act: -0.1700
Data Index: 3084833 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.7391. Min Act: -0.1700
Data Index: 4988857 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.7079. Min Act: -0.1700
Data Index: 1502790 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.6454. Min Act: -0.1700
Data Index: 283111 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.6141. Min Act: -0.1700
Data Index: 1411179 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.5829. Min Act: -0.1700
Data Index: 971270 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.5516. Min Act: -0.1700
Data Index: 1821581 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.5516. Min Act: -0.1700
Data Index: 4450212 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.4891. Min Act: -0.1700
Data Index: 4869218 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.4579. Min Act: -0.1700
Data Index: 2287184 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.4579. Min Act: -0.1700
Data Index: 1908195 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.4266. Min Act: -0.1700
Data Index: 1461476 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1766. Min Range: -8.1766
Max Act: 7.4266. Min Act: -0.1700
Data Index: 5233126 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19