Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6390. Min Range: -8.6390
Max Act: 8.6390. Min Act: -0.1700
Data Index: 348095 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6390. Min Range: -8.6390
Max Act: 8.3265. Min Act: -0.1700
Data Index: 385251 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6390. Min Range: -8.6390
Max Act: 8.1390. Min Act: -0.1700
Data Index: 2906823 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6390. Min Range: -8.6390
Max Act: 8.0765. Min Act: -0.1700
Data Index: 618703 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6390. Min Range: -8.6390
Max Act: 8.0453. Min Act: -0.1700
Data Index: 3493898 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6390. Min Range: -8.6390
Max Act: 8.0140. Min Act: -0.1700
Data Index: 7358281 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.9828. Min Act: -0.1700
Data Index: 2151581 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.9515. Min Act: -0.1700
Data Index: 6600084 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.9515. Min Act: -0.1700
Data Index: 6526312 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.8890. Min Act: -0.1700
Data Index: 3816597 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.8890. Min Act: -0.1700
Data Index: 458452 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.8890. Min Act: -0.1700
Data Index: 6600087 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.8578. Min Act: -0.1700
Data Index: 4603774 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.8578. Min Act: -0.1700
Data Index: 162652 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.8265. Min Act: -0.1700
Data Index: 4643125 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.7953. Min Act: -0.1700
Data Index: 2266910 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.7640. Min Act: -0.1700
Data Index: 4735457 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.7328. Min Act: -0.1700
Data Index: 226779 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.7640. Min Act: -0.1700
Data Index: 1536946 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6390. Min Range: -8.6390
Max Act: 7.7015. Min Act: -0.1700
Data Index: 2834972 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19