Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0511. Min Range: -8.0511
Max Act: 8.0511. Min Act: -0.1700
Data Index: 5927463 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.9573. Min Act: -0.1700
Data Index: 4034623 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.8948. Min Act: -0.1700
Data Index: 3297996 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.9573. Min Act: -0.1700
Data Index: 7610700 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.8011. Min Act: -0.1700
Data Index: 590517 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.8323. Min Act: -0.1700
Data Index: 6652780 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.8011. Min Act: -0.1700
Data Index: 7721250 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.8011. Min Act: -0.1700
Data Index: 5268633 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.6761. Min Act: -0.1700
Data Index: 4711611 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.7073. Min Act: -0.1700
Data Index: 3415085 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.4886. Min Act: -0.1700
Data Index: 1711112 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.4573. Min Act: -0.1700
Data Index: 6139813 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.5198. Min Act: -0.1700
Data Index: 4232040 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.4573. Min Act: -0.1700
Data Index: 944206 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.3948. Min Act: -0.1700
Data Index: 7512872 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.3636. Min Act: -0.1700
Data Index: 515303 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.3636. Min Act: -0.1700
Data Index: 2360058 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.3011. Min Act: -0.1700
Data Index: 8145502 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.2073. Min Act: -0.1700
Data Index: 2105827 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0511. Min Range: -8.0511
Max Act: 7.1761. Min Act: -0.1700
Data Index: 6813402 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19