Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4479 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.8361. Min Act: -0.1700
Data Index: 1336003 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.8048. Min Act: -0.1700
Data Index: 6196220 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.7423. Min Act: -0.1700
Data Index: 8125931 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.7111. Min Act: -0.1700
Data Index: 708623 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.6798. Min Act: -0.1700
Data Index: 5944981 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.6798. Min Act: -0.1700
Data Index: 8494047 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.6486. Min Act: -0.1700
Data Index: 5944982 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.6173. Min Act: -0.1700
Data Index: 7155724 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5861. Min Act: -0.1700
Data Index: 276583 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5548. Min Act: -0.1700
Data Index: 4550491 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5548. Min Act: -0.1700
Data Index: 2318589 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5548. Min Act: -0.1700
Data Index: 3189641 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5236. Min Act: -0.1700
Data Index: 1384064 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5236. Min Act: -0.1699
Data Index: 6874896 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5236. Min Act: -0.1700
Data Index: 8786613 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5236. Min Act: -0.1700
Data Index: 6396092 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5236. Min Act: -0.1700
Data Index: 8247355 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5236. Min Act: -0.1700
Data Index: 14542 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5236. Min Act: -0.1700
Data Index: 184349 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8361. Min Range: -5.8361
Max Act: 5.5236. Min Act: -0.1700
Data Index: 2987715 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19