Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.4556. Min Act: -0.1700
Data Index: 4488989 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.4556. Min Act: -0.1700
Data Index: 5183312 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.4243. Min Act: -0.1700
Data Index: 3531914 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.4243. Min Act: -0.1700
Data Index: 2618285 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.4556. Min Act: -0.1700
Data Index: 4510015 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.3306. Min Act: -0.1700
Data Index: 118074 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.3618. Min Act: -0.1700
Data Index: 8721075 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.3306. Min Act: -0.1700
Data Index: 7497062 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.3306. Min Act: -0.1700
Data Index: 4277152 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.3306. Min Act: -0.1700
Data Index: 4292304 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2993. Min Act: -0.1700
Data Index: 4649366 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.3306. Min Act: -0.1700
Data Index: 3871820 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2993. Min Act: -0.1700
Data Index: 835247 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2681. Min Act: -0.1700
Data Index: 4691865 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2681. Min Act: -0.1700
Data Index: 8107584 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2681. Min Act: -0.1700
Data Index: 8297931 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2056. Min Act: -0.1700
Data Index: 3785861 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2056. Min Act: -0.1700
Data Index: 1132135 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.1743. Min Act: -0.1700
Data Index: 874439 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2056. Min Act: -0.1700
Data Index: 1921877 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19