Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4784 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2477. Min Range: -7.2477
Max Act: 7.2477. Min Act: -0.1700
Data Index: 6704711 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2477. Min Range: -7.2477
Max Act: 7.1852. Min Act: -0.1700
Data Index: 2919587 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2477. Min Range: -7.2477
Max Act: 7.0915. Min Act: -0.1700
Data Index: 4858701 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2477. Min Range: -7.2477
Max Act: 7.0290. Min Act: -0.1700
Data Index: 3943357 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2477. Min Range: -7.2477
Max Act: 7.0602. Min Act: -0.1700
Data Index: 1568160 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.9665. Min Act: -0.1700
Data Index: 7190327 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.9352. Min Act: -0.1700
Data Index: 7964591 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.9665. Min Act: -0.1700
Data Index: 7568046 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.9352. Min Act: -0.1700
Data Index: 2340219 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.8727. Min Act: -0.1700
Data Index: 2055939 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.9352. Min Act: -0.1700
Data Index: 7242727 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.8727. Min Act: -0.1700
Data Index: 4655389 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.8727. Min Act: -0.1700
Data Index: 6693820 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.8727. Min Act: -0.1700
Data Index: 5818114 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.8415. Min Act: -0.1700
Data Index: 104849 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.8415. Min Act: -0.1700
Data Index: 3081401 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.8415. Min Act: -0.1700
Data Index: 3160435 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.8102. Min Act: -0.1700
Data Index: 7242726 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.7790. Min Act: -0.1700
Data Index: 7046643 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2477. Min Range: -7.2477
Max Act: 6.8102. Min Act: -0.1700
Data Index: 3585742 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19