Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4776 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.6666. Min Act: -0.1700
Data Index: 7884947 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.6978. Min Act: -0.1700
Data Index: 3000108 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.6666. Min Act: -0.1700
Data Index: 2174179 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.6978. Min Act: -0.1700
Data Index: 6057646 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.6353. Min Act: -0.1700
Data Index: 2747252 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.6353. Min Act: -0.1700
Data Index: 8634638 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.6041. Min Act: -0.1700
Data Index: 1369211 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5728. Min Act: -0.1700
Data Index: 3058917 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5728. Min Act: -0.1700
Data Index: 2006388 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5728. Min Act: -0.1700
Data Index: 6047204 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5728. Min Act: -0.1700
Data Index: 5408526 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5416. Min Act: -0.1700
Data Index: 4567168 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5728. Min Act: -0.1700
Data Index: 2227650 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5728. Min Act: -0.1700
Data Index: 1774824 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5416. Min Act: -0.1700
Data Index: 5728866 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5103. Min Act: -0.1700
Data Index: 5067010 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5416. Min Act: -0.1700
Data Index: 6109886 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5416. Min Act: -0.1700
Data Index: 2933815 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5416. Min Act: -0.1700
Data Index: 7053387 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6978. Min Range: -6.6978
Max Act: 6.5416. Min Act: -0.1700
Data Index: 4005409 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19