Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.9765. Min Act: -0.1700
Data Index: 4763296 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.7890. Min Act: -0.1700
Data Index: 5185522 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.7265. Min Act: -0.1700
Data Index: 1523270 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.7265. Min Act: -0.1700
Data Index: 7870414 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.6640. Min Act: -0.1700
Data Index: 3752506 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.6640. Min Act: -0.1700
Data Index: 2758344 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.6640. Min Act: -0.1700
Data Index: 1212036 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.6640. Min Act: -0.1700
Data Index: 8483042 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.6015. Min Act: -0.1700
Data Index: 1791963 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.6015. Min Act: -0.1700
Data Index: 5573214 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.5390. Min Act: -0.1700
Data Index: 973005 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.5390. Min Act: -0.1700
Data Index: 7202597 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.5390. Min Act: -0.1700
Data Index: 7361565 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.4765. Min Act: -0.1700
Data Index: 5736376 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.4765. Min Act: -0.1700
Data Index: 6593147 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.5390. Min Act: -0.1700
Data Index: 8414533 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.4765. Min Act: -0.1700
Data Index: 2876479 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.4765. Min Act: -0.1700
Data Index: 1591845 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.4765. Min Act: -0.1700
Data Index: 1988631 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9765. Min Range: -8.9765
Max Act: 8.4765. Min Act: -0.1700
Data Index: 3403193 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19