Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.9398. Min Act: -0.1700
Data Index: 6034303 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.6898. Min Act: -0.1700
Data Index: 2090702 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.6273. Min Act: -0.1700
Data Index: 2751318 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.5648. Min Act: -0.1700
Data Index: 2090703 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.5023. Min Act: -0.1700
Data Index: 4028767 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.5023. Min Act: -0.1699
Data Index: 740545 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.4398. Min Act: -0.1700
Data Index: 2079026 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.4398. Min Act: -0.1700
Data Index: 7185699 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.3773. Min Act: -0.1700
Data Index: 3811043 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.2523. Min Act: -0.1700
Data Index: 4899558 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.2523. Min Act: -0.1700
Data Index: 7153548 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.3148. Min Act: -0.1700
Data Index: 7624075 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.2523. Min Act: -0.1700
Data Index: 2277505 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.2523. Min Act: -0.1700
Data Index: 7069208 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.2523. Min Act: -0.1700
Data Index: 5423849 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.2523. Min Act: -0.1700
Data Index: 3894201 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.2523. Min Act: -0.1700
Data Index: 5180060 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.1898. Min Act: -0.1700
Data Index: 740548 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.1898. Min Act: -0.1700
Data Index: 718965 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9398. Min Range: -8.9398
Max Act: 8.1898. Min Act: -0.1700
Data Index: 1581144 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19