Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1527 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.4539. Min Act: -0.1700
Data Index: 5397552 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.4226. Min Act: -0.1700
Data Index: 5711514 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3914. Min Act: -0.1700
Data Index: 6221508 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3601. Min Act: -0.1700
Data Index: 5933587 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3601. Min Act: -0.1700
Data Index: 8417970 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3601. Min Act: -0.1700
Data Index: 6133565 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3289. Min Act: -0.1700
Data Index: 5159463 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3289. Min Act: -0.1700
Data Index: 4556271 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2976. Min Act: -0.1700
Data Index: 7637860 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3289. Min Act: -0.1700
Data Index: 573694 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2976. Min Act: -0.1700
Data Index: 1822658 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2976. Min Act: -0.1700
Data Index: 3807810 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3289. Min Act: -0.1700
Data Index: 3669118 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2351. Min Act: -0.1700
Data Index: 2623085 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2664. Min Act: -0.1700
Data Index: 7868335 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2664. Min Act: -0.1700
Data Index: 727939 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2664. Min Act: -0.1700
Data Index: 3284331 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2664. Min Act: -0.1700
Data Index: 8610305 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2351. Min Act: -0.1700
Data Index: 8586863 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2351. Min Act: -0.1700
Data Index: 5105019 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19