Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3527 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1477. Min Range: -5.1477
Max Act: 5.1477. Min Act: -0.1700
Data Index: 2640954 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.9914. Min Act: -0.1700
Data Index: 674941 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.9914. Min Act: -0.1700
Data Index: 6993967 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.9289. Min Act: -0.1700
Data Index: 8809636 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.8352. Min Act: -0.1700
Data Index: 7923000 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.8352. Min Act: -0.1700
Data Index: 1248645 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.8039. Min Act: -0.1700
Data Index: 5356114 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.7727. Min Act: -0.1700
Data Index: 1579546 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.7414. Min Act: -0.1700
Data Index: 748246 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.7414. Min Act: -0.1700
Data Index: 2914803 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.7414. Min Act: -0.1699
Data Index: 8081771 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.7414. Min Act: -0.1700
Data Index: 2314619 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.7414. Min Act: -0.1700
Data Index: 8460358 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.7102. Min Act: -0.1700
Data Index: 300792 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.7102. Min Act: -0.1700
Data Index: 1924716 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.7102. Min Act: -0.1700
Data Index: 8593880 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.6789. Min Act: -0.1700
Data Index: 1544939 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.6789. Min Act: -0.1700
Data Index: 1757336 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.6789. Min Act: -0.1700
Data Index: 3884448 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1477. Min Range: -5.1477
Max Act: 4.7102. Min Act: -0.1700
Data Index: 3240844 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19