Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4964 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.5229. Min Act: -0.1700
Data Index: 1682653 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.5229. Min Act: -0.1700
Data Index: 4970898 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.4604. Min Act: -0.1700
Data Index: 5940737 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.4604. Min Act: -0.1700
Data Index: 8506086 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.4291. Min Act: -0.1700
Data Index: 7260663 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.4291. Min Act: -0.1700
Data Index: 4970912 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3979. Min Act: -0.1700
Data Index: 6525964 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3979. Min Act: -0.1700
Data Index: 3560450 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3666. Min Act: -0.1700
Data Index: 3795116 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3666. Min Act: -0.1700
Data Index: 7167512 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3666. Min Act: -0.1700
Data Index: 6209035 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3354. Min Act: -0.1700
Data Index: 2646293 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3354. Min Act: -0.1700
Data Index: 1746975 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3041. Min Act: -0.1700
Data Index: 2858774 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3354. Min Act: -0.1700
Data Index: 2943631 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.2729. Min Act: -0.1700
Data Index: 5056214 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3041. Min Act: -0.1700
Data Index: 1606633 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3041. Min Act: -0.1700
Data Index: 7430882 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3041. Min Act: -0.1700
Data Index: 1433592 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5229. Min Range: -5.5229
Max Act: 5.3041. Min Act: -0.1700
Data Index: 6351392 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19