Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2912 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.5709. Min Act: -0.1700
Data Index: 1163019 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.5084. Min Act: -0.1688
Data Index: 5302994 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.3209. Min Act: -0.1700
Data Index: 2829312 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.1959. Min Act: -0.1700
Data Index: 2591258 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.1959. Min Act: -0.1700
Data Index: 5803263 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.1959. Min Act: -0.1700
Data Index: 5260822 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.1959. Min Act: -0.1700
Data Index: 1387724 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.1959. Min Act: -0.1700
Data Index: 554998 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.1959. Min Act: -0.1699
Data Index: 5506665 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.1959. Min Act: -0.1700
Data Index: 2512893 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.1959. Min Act: -0.1700
Data Index: 5989755 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.1334. Min Act: -0.1700
Data Index: 3396367 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.1334. Min Act: -0.1700
Data Index: 2477461 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.0084. Min Act: -0.1700
Data Index: 6433543 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5709. Min Range: -12.5709
Max Act: 12.0084. Min Act: -0.1700
Data Index: 7597411 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5709. Min Range: -12.5709
Max Act: 11.9459. Min Act: -0.1700
Data Index: 4830370 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5709. Min Range: -12.5709
Max Act: 11.9459. Min Act: -0.1700
Data Index: 5964931 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5709. Min Range: -12.5709
Max Act: 11.8834. Min Act: -0.1700
Data Index: 220413 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5709. Min Range: -12.5709
Max Act: 11.8209. Min Act: -0.1700
Data Index: 3905771 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5709. Min Range: -12.5709
Max Act: 11.7584. Min Act: -0.1700
Data Index: 3241606 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19