Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.8887. Min Act: -0.1700
Data Index: 4829073 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.9200. Min Act: -0.1700
Data Index: 70590 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.8887. Min Act: -0.1700
Data Index: 8201917 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.7637. Min Act: -0.1700
Data Index: 2106532 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.7637. Min Act: -0.1700
Data Index: 977569 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.7637. Min Act: -0.1700
Data Index: 719381 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.7325. Min Act: -0.1700
Data Index: 1957709 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.7325. Min Act: -0.1700
Data Index: 3446903 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.7012. Min Act: -0.1700
Data Index: 6449956 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.7012. Min Act: -0.1700
Data Index: 98000 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.6700. Min Act: -0.1700
Data Index: 5644187 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.7012. Min Act: -0.1700
Data Index: 3105494 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.6700. Min Act: -0.1700
Data Index: 3194187 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.6700. Min Act: -0.1700
Data Index: 7301624 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.6387. Min Act: -0.1700
Data Index: 3518872 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.6700. Min Act: -0.1700
Data Index: 8574463 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.6387. Min Act: -0.1700
Data Index: 1089272 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.6387. Min Act: -0.1700
Data Index: 7556533 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.6387. Min Act: -0.1700
Data Index: 3837379 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9200. Min Range: -4.9200
Max Act: 4.6387. Min Act: -0.1700
Data Index: 133093 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19