Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3913 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0654. Min Range: -4.0654
Max Act: 4.0654. Min Act: -0.1700
Data Index: 6501384 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.9403. Min Act: -0.1700
Data Index: 3051896 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.9091. Min Act: -0.1700
Data Index: 3637927 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8778. Min Act: -0.1700
Data Index: 8701957 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8778. Min Act: -0.1700
Data Index: 6133493 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8465. Min Act: -0.1700
Data Index: 8120340 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8465. Min Act: -0.1700
Data Index: 3051895 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8465. Min Act: -0.1700
Data Index: 8288089 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8465. Min Act: -0.1700
Data Index: 4811852 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8465. Min Act: -0.1700
Data Index: 2591549 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8152. Min Act: -0.1700
Data Index: 2800077 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8152. Min Act: -0.1700
Data Index: 3763771 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8152. Min Act: -0.1700
Data Index: 1528982 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8152. Min Act: -0.1700
Data Index: 7189824 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8152. Min Act: -0.1700
Data Index: 1640868 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8465. Min Act: -0.1700
Data Index: 4013753 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.7840. Min Act: -0.1700
Data Index: 1317012 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8152. Min Act: -0.1700
Data Index: 1308527 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.8152. Min Act: -0.1700
Data Index: 3066484 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.7840. Min Act: -0.1700
Data Index: 4238626 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19