Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2964 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.9454. Min Act: -0.1700
Data Index: 1788678 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.9454. Min Act: -0.1700
Data Index: 4413689 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.8516. Min Act: -0.1700
Data Index: 1694569 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.8516. Min Act: -0.1700
Data Index: 4900824 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.7579. Min Act: -0.1700
Data Index: 7346433 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.7579. Min Act: -0.1700
Data Index: 4336121 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6954. Min Act: -0.1700
Data Index: 7751312 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6641. Min Act: -0.1700
Data Index: 3606921 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6641. Min Act: -0.1700
Data Index: 7446817 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6641. Min Act: -0.1700
Data Index: 7249901 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6329. Min Act: -0.1700
Data Index: 5071097 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6329. Min Act: -0.1700
Data Index: 4453529 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6329. Min Act: -0.1700
Data Index: 6312702 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6329. Min Act: -0.1700
Data Index: 1721803 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5391. Min Act: -0.1700
Data Index: 4127199 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5391. Min Act: -0.1700
Data Index: 5559479 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5391. Min Act: -0.1700
Data Index: 2105604 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5079. Min Act: -0.1700
Data Index: 4831420 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5079. Min Act: -0.1700
Data Index: 8515855 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5079. Min Act: -0.1700
Data Index: 906995 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19