Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1384 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.9620. Min Act: -0.1700
Data Index: 445675 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.9620. Min Act: -0.1700
Data Index: 2098629 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8995. Min Act: -0.1700
Data Index: 8602732 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.7745. Min Act: -0.1700
Data Index: 1719051 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.7433. Min Act: -0.1700
Data Index: 7944225 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.7120. Min Act: -0.1700
Data Index: 103892 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.7120. Min Act: -0.1700
Data Index: 2235600 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.7120. Min Act: -0.1700
Data Index: 3979862 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.6495. Min Act: -0.1700
Data Index: 2828464 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.6495. Min Act: -0.1700
Data Index: 8826605 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.6183. Min Act: -0.1700
Data Index: 2788120 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.6183. Min Act: -0.1700
Data Index: 58368 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.6183. Min Act: -0.1700
Data Index: 2526067 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.6183. Min Act: -0.1700
Data Index: 7988271 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.5870. Min Act: -0.1700
Data Index: 5026015 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.5870. Min Act: -0.1700
Data Index: 6673657 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.5870. Min Act: -0.1700
Data Index: 975691 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.6183. Min Act: -0.1700
Data Index: 5560252 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.5558. Min Act: -0.1700
Data Index: 40570 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.5558. Min Act: -0.1700
Data Index: 6257921 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19