Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3955 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.5482. Min Act: -0.1700
Data Index: 4632869 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.5170. Min Act: -0.1700
Data Index: 2048896 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.4857. Min Act: -0.1700
Data Index: 8800986 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.4857. Min Act: -0.1700
Data Index: 2040021 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.3920. Min Act: -0.1700
Data Index: 2062339 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.3607. Min Act: -0.1700
Data Index: 6277057 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.3295. Min Act: -0.1700
Data Index: 2815683 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.3607. Min Act: -0.1700
Data Index: 3366059 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.3607. Min Act: -0.1700
Data Index: 3466168 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.3295. Min Act: -0.1700
Data Index: 4621930 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.2670. Min Act: -0.1700
Data Index: 2815687 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.2982. Min Act: -0.1700
Data Index: 363145 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.2982. Min Act: -0.1700
Data Index: 7569084 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.2670. Min Act: -0.1700
Data Index: 3111385 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.2670. Min Act: -0.1700
Data Index: 5149636 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.2670. Min Act: -0.1700
Data Index: 910828 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.2670. Min Act: -0.1700
Data Index: 5372896 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.2357. Min Act: -0.1700
Data Index: 3839118 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.2357. Min Act: -0.1700
Data Index: 4760124 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5482. Min Range: -4.5482
Max Act: 4.2357. Min Act: -0.1700
Data Index: 8017591 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19