Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0298. Min Range: -7.0298
Max Act: 7.0298. Min Act: -0.1700
Data Index: 8015514 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.9673. Min Act: -0.1700
Data Index: 641857 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.9673. Min Act: -0.1700
Data Index: 5816838 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.9048. Min Act: -0.1700
Data Index: 5097367 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.9048. Min Act: -0.1700
Data Index: 6224851 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.8736. Min Act: -0.1700
Data Index: 3276115 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.9048. Min Act: -0.1700
Data Index: 8118369 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.8736. Min Act: -0.1700
Data Index: 2049646 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.8423. Min Act: -0.1700
Data Index: 536023 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.8111. Min Act: -0.1700
Data Index: 5929332 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.7798. Min Act: -0.1700
Data Index: 3394607 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.7486. Min Act: -0.1700
Data Index: 6494478 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.7486. Min Act: -0.1700
Data Index: 7470929 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.7486. Min Act: -0.1700
Data Index: 2347012 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.7486. Min Act: -0.1700
Data Index: 1226536 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.6861. Min Act: -0.1700
Data Index: 7060333 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.6548. Min Act: -0.1700
Data Index: 4205081 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.6548. Min Act: -0.1700
Data Index: 8562624 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.6236. Min Act: -0.1700
Data Index: 2574579 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0298. Min Range: -7.0298
Max Act: 6.6548. Min Act: -0.1700
Data Index: 5521075 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19