Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2446 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2072. Min Range: -6.2072
Max Act: 6.2072. Min Act: -0.1700
Data Index: 628498 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.9885. Min Act: -0.1700
Data Index: 5951085 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.9260. Min Act: -0.1700
Data Index: 3822124 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.8635. Min Act: -0.1700
Data Index: 2512634 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.8322. Min Act: -0.1700
Data Index: 5064108 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.8010. Min Act: -0.1700
Data Index: 2757700 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.7697. Min Act: -0.1700
Data Index: 3959801 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.7385. Min Act: -0.1700
Data Index: 6225815 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.7072. Min Act: -0.1700
Data Index: 5107343 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.7385. Min Act: -0.1700
Data Index: 7075414 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.7072. Min Act: -0.1700
Data Index: 7524886 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.6760. Min Act: -0.1700
Data Index: 7695632 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.6760. Min Act: -0.1700
Data Index: 3228458 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.6760. Min Act: -0.1700
Data Index: 521420 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.6760. Min Act: -0.1700
Data Index: 5553067 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.6760. Min Act: -0.1700
Data Index: 6537064 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.6760. Min Act: -0.1700
Data Index: 1768992 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.6760. Min Act: -0.1700
Data Index: 7204927 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.6447. Min Act: -0.1700
Data Index: 4581215 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2072. Min Range: -6.2072
Max Act: 5.6760. Min Act: -0.1700
Data Index: 6394766 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19