Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2099. Min Range: -10.2099
Max Act: 10.2099. Min Act: -0.1700
Data Index: 7313510 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2099. Min Range: -10.2099
Max Act: 10.0224. Min Act: -0.1700
Data Index: 6322228 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.8974. Min Act: -0.1700
Data Index: 7439367 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.8349. Min Act: -0.1700
Data Index: 7313511 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.7724. Min Act: -0.1700
Data Index: 2449880 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.7099. Min Act: -0.1700
Data Index: 6166173 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.6474. Min Act: -0.1700
Data Index: 6547646 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.6474. Min Act: -0.1700
Data Index: 7608246 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5849. Min Act: -0.1700
Data Index: 1966353 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5849. Min Act: -0.1700
Data Index: 6741475 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5224. Min Act: -0.1700
Data Index: 6424764 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5849. Min Act: -0.1700
Data Index: 1027089 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5849. Min Act: -0.1700
Data Index: 1018938 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5849. Min Act: -0.1700
Data Index: 6048195 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5224. Min Act: -0.1700
Data Index: 6048197 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5224. Min Act: -0.1700
Data Index: 905000 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5849. Min Act: -0.1700
Data Index: 904998 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5849. Min Act: -0.1700
Data Index: 4898420 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5849. Min Act: -0.1700
Data Index: 785334 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2099. Min Range: -10.2099
Max Act: 9.5849. Min Act: -0.1700
Data Index: 3693143 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19