Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2653. Min Range: -5.2653
Max Act: 5.2653. Min Act: -0.1700
Data Index: 7739108 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2653. Min Range: -5.2653
Max Act: 5.2028. Min Act: -0.1700
Data Index: 3360919 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2653. Min Range: -5.2653
Max Act: 5.2028. Min Act: -0.1700
Data Index: 4890288 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2653. Min Range: -5.2653
Max Act: 5.1403. Min Act: -0.1700
Data Index: 7739109 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2653. Min Range: -5.2653
Max Act: 5.1090. Min Act: -0.1700
Data Index: 4323462 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2653. Min Range: -5.2653
Max Act: 5.0778. Min Act: -0.1700
Data Index: 5913930 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2653. Min Range: -5.2653
Max Act: 5.0778. Min Act: -0.1700
Data Index: 4037698 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2653. Min Range: -5.2653
Max Act: 5.0153. Min Act: -0.1700
Data Index: 7468851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2653. Min Range: -5.2653
Max Act: 5.0153. Min Act: -0.1700
Data Index: 3526196 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2653. Min Range: -5.2653
Max Act: 4.9840. Min Act: -0.1700
Data Index: 3543991 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2653. Min Range: -5.2653
Max Act: 5.0153. Min Act: -0.1700
Data Index: 4695135 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2653. Min Range: -5.2653
Max Act: 5.0153. Min Act: -0.1700
Data Index: 7625441 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2653. Min Range: -5.2653
Max Act: 4.9840. Min Act: -0.1700
Data Index: 7708018 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2653. Min Range: -5.2653
Max Act: 4.9840. Min Act: -0.1700
Data Index: 4108970 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2653. Min Range: -5.2653
Max Act: 4.9840. Min Act: -0.1700
Data Index: 3717425 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2653. Min Range: -5.2653
Max Act: 4.9840. Min Act: -0.1700
Data Index: 7812098 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2653. Min Range: -5.2653
Max Act: 4.9840. Min Act: -0.1700
Data Index: 3462473 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2653. Min Range: -5.2653
Max Act: 4.9840. Min Act: -0.1700
Data Index: 8411546 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2653. Min Range: -5.2653
Max Act: 4.9528. Min Act: -0.1700
Data Index: 3678943 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2653. Min Range: -5.2653
Max Act: 4.9528. Min Act: -0.1700
Data Index: 4355769 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19