Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1225 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2841. Min Range: -6.2841
Max Act: 6.2841. Min Act: -0.1700
Data Index: 5926952 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2841. Min Range: -6.2841
Max Act: 6.1903. Min Act: -0.1700
Data Index: 1880359 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2841. Min Range: -6.2841
Max Act: 6.0653. Min Act: -0.1700
Data Index: 5499171 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.9403. Min Act: -0.1700
Data Index: 6250652 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.6903. Min Act: -0.1700
Data Index: 3843897 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.7216. Min Act: -0.1700
Data Index: 2101259 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.6591. Min Act: -0.1700
Data Index: 7166329 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.6278. Min Act: -0.1700
Data Index: 8108003 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5966. Min Act: -0.1700
Data Index: 1828139 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5966. Min Act: -0.1700
Data Index: 7768855 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5966. Min Act: -0.1700
Data Index: 4295604 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5966. Min Act: -0.1700
Data Index: 8160278 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5653. Min Act: -0.1700
Data Index: 256403 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5966. Min Act: -0.1700
Data Index: 173712 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5653. Min Act: -0.1700
Data Index: 192007 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5341. Min Act: -0.1700
Data Index: 6666362 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5341. Min Act: -0.1700
Data Index: 6505062 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5028. Min Act: -0.1700
Data Index: 7390940 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5028. Min Act: -0.1700
Data Index: 7428732 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2841. Min Range: -6.2841
Max Act: 5.5028. Min Act: -0.1700
Data Index: 275717 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19