Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0498. Min Range: -6.0498
Max Act: 6.0498. Min Act: -0.1700
Data Index: 8704409 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.9873. Min Act: -0.1700
Data Index: 8131995 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.8311. Min Act: -0.1700
Data Index: 4588266 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.7998. Min Act: -0.1700
Data Index: 5505243 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.7373. Min Act: -0.1700
Data Index: 2638226 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.7061. Min Act: -0.1700
Data Index: 107596 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.6748. Min Act: -0.1700
Data Index: 2900534 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.6748. Min Act: -0.1700
Data Index: 2479406 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.6748. Min Act: -0.1700
Data Index: 7338685 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.6748. Min Act: -0.1700
Data Index: 4435413 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.6123. Min Act: -0.1700
Data Index: 3133365 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.5811. Min Act: -0.1700
Data Index: 787437 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.6123. Min Act: -0.1700
Data Index: 564178 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.6123. Min Act: -0.1700
Data Index: 7810891 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.6123. Min Act: -0.1700
Data Index: 6328906 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.6123. Min Act: -0.1700
Data Index: 8719468 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.5811. Min Act: -0.1700
Data Index: 4555939 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.5811. Min Act: -0.1700
Data Index: 88533 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.5811. Min Act: -0.1700
Data Index: 2982511 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0498. Min Range: -6.0498
Max Act: 5.5498. Min Act: -0.1700
Data Index: 581969 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19