Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0722. Min Range: -7.0722
Max Act: 7.0722. Min Act: -0.1700
Data Index: 4368796 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.7284. Min Act: -0.1700
Data Index: 5253941 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.6659. Min Act: -0.1700
Data Index: 504905 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.6034. Min Act: -0.1700
Data Index: 1300075 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.6034. Min Act: -0.1700
Data Index: 1029802 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.5097. Min Act: -0.1700
Data Index: 2051514 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.4784. Min Act: -0.1700
Data Index: 4056415 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.4472. Min Act: -0.1700
Data Index: 4206468 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.4472. Min Act: -0.1700
Data Index: 3600607 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.4472. Min Act: -0.1700
Data Index: 4810053 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.4159. Min Act: -0.1700
Data Index: 3842560 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.4159. Min Act: -0.1700
Data Index: 6005831 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.4159. Min Act: -0.1700
Data Index: 6639715 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.4159. Min Act: -0.1700
Data Index: 2432345 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.3847. Min Act: -0.1700
Data Index: 5028714 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.3847. Min Act: -0.1700
Data Index: 1468555 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.3222. Min Act: -0.1700
Data Index: 1787043 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.3222. Min Act: -0.1700
Data Index: 1067716 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.3222. Min Act: -0.1700
Data Index: 5645336 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0722. Min Range: -7.0722
Max Act: 6.2909. Min Act: -0.1700
Data Index: 5075760 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19