Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4677 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.9479. Min Act: -0.1700
Data Index: 3265313 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.7917. Min Act: -0.1700
Data Index: 8136271 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.6667. Min Act: -0.1700
Data Index: 7786587 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.6667. Min Act: -0.1700
Data Index: 8135700 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.6042. Min Act: -0.1700
Data Index: 3656808 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.6042. Min Act: -0.1700
Data Index: 6232422 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.5729. Min Act: -0.1700
Data Index: 6971991 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.5417. Min Act: -0.1700
Data Index: 681283 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.5417. Min Act: -0.1700
Data Index: 3407829 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.5417. Min Act: -0.1700
Data Index: 4171695 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.5104. Min Act: -0.1700
Data Index: 1260359 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.5104. Min Act: -0.1700
Data Index: 3357775 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.4479. Min Act: -0.1700
Data Index: 898839 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.4167. Min Act: -0.1700
Data Index: 4996880 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.4167. Min Act: -0.1700
Data Index: 285180 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.4167. Min Act: -0.1700
Data Index: 1857364 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.3854. Min Act: -0.1700
Data Index: 6371870 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.3854. Min Act: -0.1700
Data Index: 4625916 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.4167. Min Act: -0.1700
Data Index: 1396899 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9479. Min Range: -6.9479
Max Act: 6.4167. Min Act: -0.1700
Data Index: 8789281 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19