Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.6936. Min Act: -0.1700
Data Index: 3135895 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.4436. Min Act: -0.1700
Data Index: 6224658 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.3186. Min Act: -0.1700
Data Index: 3570622 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.3186. Min Act: -0.1700
Data Index: 3570636 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.3186. Min Act: -0.1700
Data Index: 5709360 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.3186. Min Act: -0.1700
Data Index: 6645452 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.2561. Min Act: -0.1700
Data Index: 1778175 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1936. Min Act: -0.1700
Data Index: 1124476 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1936. Min Act: -0.1700
Data Index: 812252 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1936. Min Act: -0.1700
Data Index: 5307113 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1936. Min Act: -0.1700
Data Index: 4022360 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1311. Min Act: -0.1700
Data Index: 8438995 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1936. Min Act: -0.1700
Data Index: 5709327 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1311. Min Act: -0.1700
Data Index: 6771966 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1311. Min Act: -0.1700
Data Index: 3570632 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.0686. Min Act: -0.1700
Data Index: 1778158 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1311. Min Act: -0.1700
Data Index: 3570635 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1311. Min Act: -0.1700
Data Index: 2587019 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1311. Min Act: -0.1700
Data Index: 1922721 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6936. Min Range: -8.6936
Max Act: 8.1311. Min Act: -0.1700
Data Index: 5709323 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19