Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3791 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1032. Min Range: -4.1032
Max Act: 4.1032. Min Act: -0.1700
Data Index: 1184979 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1032. Min Range: -4.1032
Max Act: 4.0407. Min Act: -0.1700
Data Index: 1219859 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1032. Min Range: -4.1032
Max Act: 4.0094. Min Act: -0.1700
Data Index: 3656229 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.9782. Min Act: -0.1700
Data Index: 4578594 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.9782. Min Act: -0.1700
Data Index: 5719637 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.9469. Min Act: -0.1700
Data Index: 2588643 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.9469. Min Act: -0.1700
Data Index: 7486704 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.9000. Min Act: -0.1700
Data Index: 4999986 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.9313. Min Act: -0.1700
Data Index: 358855 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.9000. Min Act: -0.1700
Data Index: 7406203 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.9000. Min Act: -0.1700
Data Index: 4929029 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.8687. Min Act: -0.1700
Data Index: 5859781 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.8687. Min Act: -0.1700
Data Index: 6480034 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.8687. Min Act: -0.1700
Data Index: 7269609 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.8687. Min Act: -0.1700
Data Index: 751494 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.8687. Min Act: -0.1700
Data Index: 515624 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.8531. Min Act: -0.1700
Data Index: 6024682 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.8375. Min Act: -0.1700
Data Index: 945916 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.8375. Min Act: -0.1700
Data Index: 4091457 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1032. Min Range: -4.1032
Max Act: 3.8218. Min Act: -0.1700
Data Index: 6736566 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19