Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3129 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.3332. Min Act: -0.1700
Data Index: 793624 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.3332. Min Act: -0.1700
Data Index: 6704133 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.3019. Min Act: -0.1700
Data Index: 2782928 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.2707. Min Act: -0.1700
Data Index: 7655100 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.2394. Min Act: -0.1700
Data Index: 4322575 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.2394. Min Act: -0.1700
Data Index: 7681241 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.2082. Min Act: -0.1700
Data Index: 618592 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.1769. Min Act: -0.1700
Data Index: 3645725 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.1457. Min Act: -0.1700
Data Index: 5751461 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.1457. Min Act: -0.1700
Data Index: 7145607 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.1144. Min Act: -0.1700
Data Index: 6317859 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.1144. Min Act: -0.1700
Data Index: 8344882 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.0832. Min Act: -0.1700
Data Index: 7961359 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.0207. Min Act: -0.1700
Data Index: 851150 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.0207. Min Act: -0.1700
Data Index: 7530284 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.0207. Min Act: -0.1700
Data Index: 4127194 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3332. Min Range: -7.3332
Max Act: 7.0207. Min Act: -0.1700
Data Index: 6164433 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3332. Min Range: -7.3332
Max Act: 6.9894. Min Act: -0.1700
Data Index: 3431888 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3332. Min Range: -7.3332
Max Act: 6.9582. Min Act: -0.1700
Data Index: 1229219 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3332. Min Range: -7.3332
Max Act: 6.9582. Min Act: -0.1700
Data Index: 416668 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19