Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1704 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0867. Min Range: -6.0867
Max Act: 6.0867. Min Act: -0.1700
Data Index: 7017774 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.9929. Min Act: -0.1700
Data Index: 5926864 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.8992. Min Act: -0.1700
Data Index: 5746543 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.8679. Min Act: -0.1700
Data Index: 4939406 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.8679. Min Act: -0.1700
Data Index: 6361928 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.8367. Min Act: -0.1700
Data Index: 6199256 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.8367. Min Act: -0.1700
Data Index: 650887 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.8367. Min Act: -0.1700
Data Index: 1527385 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.8367. Min Act: -0.1700
Data Index: 6914335 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.8054. Min Act: -0.1700
Data Index: 843668 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.8054. Min Act: -0.1700
Data Index: 3870173 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.7742. Min Act: -0.1700
Data Index: 5581561 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.7117. Min Act: -0.1700
Data Index: 6745938 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.7429. Min Act: -0.1700
Data Index: 7550348 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.7429. Min Act: -0.1700
Data Index: 7630047 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.7429. Min Act: -0.1700
Data Index: 2129947 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.7742. Min Act: -0.1700
Data Index: 3870171 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.7429. Min Act: -0.1700
Data Index: 8044136 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.7429. Min Act: -0.1700
Data Index: 5501900 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0867. Min Range: -6.0867
Max Act: 5.7117. Min Act: -0.1700
Data Index: 1640150 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19