Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5113 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.7494. Min Act: -0.1700
Data Index: 7485226 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.6086. Min Act: -0.1700
Data Index: 700156 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.6086. Min Act: -0.1700
Data Index: 3494052 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.5930. Min Act: -0.1700
Data Index: 2529527 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.5773. Min Act: -0.1700
Data Index: 4750599 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.5773. Min Act: -0.1700
Data Index: 2340918 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.5617. Min Act: -0.1700
Data Index: 5412776 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.5460. Min Act: -0.1700
Data Index: 2492796 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.5304. Min Act: -0.1700
Data Index: 6419276 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.5304. Min Act: -0.1700
Data Index: 2563078 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.5304. Min Act: -0.1700
Data Index: 8648979 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.5147. Min Act: -0.1700
Data Index: 7035799 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.5147. Min Act: -0.1700
Data Index: 2292339 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.4990. Min Act: -0.1700
Data Index: 5229268 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.4834. Min Act: -0.1700
Data Index: 6810884 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.4834. Min Act: -0.1700
Data Index: 3087983 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.4990. Min Act: -0.1700
Data Index: 4938653 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.4677. Min Act: -0.1700
Data Index: 3173150 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.4677. Min Act: -0.1700
Data Index: 8168703 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7494. Min Range: -3.7494
Max Act: 3.4520. Min Act: -0.1700
Data Index: 7129266 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19