Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1673 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.8338. Min Act: -0.1700
Data Index: 6205638 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.6930. Min Act: -0.1680
Data Index: 90221 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.6461. Min Act: -0.1700
Data Index: 6520738 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.6148. Min Act: -0.1688
Data Index: 3859380 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.5678. Min Act: -0.1700
Data Index: 5225861 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.5678. Min Act: -0.1700
Data Index: 4006570 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.5365. Min Act: -0.1680
Data Index: 1302516 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.5208. Min Act: -0.1700
Data Index: 5837124 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.5365. Min Act: -0.1700
Data Index: 6543799 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.5208. Min Act: -0.1700
Data Index: 6985048 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.4895. Min Act: -0.1700
Data Index: 1341883 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.5052. Min Act: -0.1698
Data Index: 5129186 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.5052. Min Act: -0.1700
Data Index: 7177400 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.4895. Min Act: -0.1700
Data Index: 3806379 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.4895. Min Act: -0.1700
Data Index: 7578659 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.4895. Min Act: -0.1700
Data Index: 1077995 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.4739. Min Act: -0.1688
Data Index: 3051079 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.4739. Min Act: -0.1700
Data Index: 511649 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.4739. Min Act: -0.1700
Data Index: 5704727 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8338. Min Range: -3.8338
Max Act: 3.4582. Min Act: -0.1700
Data Index: 6416815 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19