Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3013 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2759. Min Range: -6.2759
Max Act: 6.2759. Min Act: -0.1700
Data Index: 4916610 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2759. Min Range: -6.2759
Max Act: 6.0884. Min Act: -0.1700
Data Index: 3187498 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2759. Min Range: -6.2759
Max Act: 6.0259. Min Act: -0.1700
Data Index: 3745457 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2759. Min Range: -6.2759
Max Act: 6.0259. Min Act: -0.1700
Data Index: 3523404 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.9946. Min Act: -0.1700
Data Index: 4936880 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.9634. Min Act: -0.1700
Data Index: 8011429 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.9634. Min Act: -0.1700
Data Index: 4852942 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.9321. Min Act: -0.1700
Data Index: 5471577 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.9321. Min Act: -0.1700
Data Index: 2804111 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.9321. Min Act: -0.1700
Data Index: 5246130 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.9009. Min Act: -0.1700
Data Index: 3042386 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.8696. Min Act: -0.1700
Data Index: 8011415 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.8696. Min Act: -0.1700
Data Index: 2991309 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.8696. Min Act: -0.1700
Data Index: 7441913 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.8384. Min Act: -0.1700
Data Index: 8612956 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.8384. Min Act: -0.1700
Data Index: 8572922 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.8696. Min Act: -0.1700
Data Index: 1554335 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.8071. Min Act: -0.1700
Data Index: 1141203 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.8071. Min Act: -0.1700
Data Index: 3553113 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2759. Min Range: -6.2759
Max Act: 5.8071. Min Act: -0.1700
Data Index: 558891 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19