Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1493 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.9098. Min Act: -0.1700
Data Index: 790936 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.8785. Min Act: -0.1700
Data Index: 7675376 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.8785. Min Act: -0.1700
Data Index: 109406 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.8473. Min Act: -0.1700
Data Index: 8017316 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.7223. Min Act: -0.1700
Data Index: 5492468 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.7535. Min Act: -0.1700
Data Index: 133010 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.7535. Min Act: -0.1700
Data Index: 7856060 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.6910. Min Act: -0.1700
Data Index: 650584 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.6598. Min Act: -0.1700
Data Index: 1203687 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.6598. Min Act: -0.1700
Data Index: 7188794 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.6598. Min Act: -0.1700
Data Index: 837031 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.5973. Min Act: -0.1700
Data Index: 5100732 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.5973. Min Act: -0.1700
Data Index: 1891346 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.5660. Min Act: -0.1700
Data Index: 1747679 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.5348. Min Act: -0.1700
Data Index: 2323888 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.5035. Min Act: -0.1700
Data Index: 128972 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.5348. Min Act: -0.1700
Data Index: 1308557 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.5348. Min Act: -0.1700
Data Index: 8697867 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.5348. Min Act: -0.1700
Data Index: 7808750 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9098. Min Range: -6.9098
Max Act: 6.5035. Min Act: -0.1700
Data Index: 510675 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19