Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5131 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.4804. Min Act: -0.1700
Data Index: 3562526 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.1991. Min Act: -0.1700
Data Index: 2510825 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.2304. Min Act: -0.1700
Data Index: 8024899 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.1991. Min Act: -0.1700
Data Index: 6797369 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.1679. Min Act: -0.1700
Data Index: 8201850 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.1054. Min Act: -0.1700
Data Index: 4846830 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.1054. Min Act: -0.1700
Data Index: 4382895 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.1054. Min Act: -0.1700
Data Index: 6858292 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.0741. Min Act: -0.1700
Data Index: 8661705 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.0741. Min Act: -0.1700
Data Index: 5380598 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.0429. Min Act: -0.1700
Data Index: 1983955 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.0116. Min Act: -0.1700
Data Index: 6992024 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4804. Min Range: -6.4804
Max Act: 6.0116. Min Act: -0.1700
Data Index: 5080005 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4804. Min Range: -6.4804
Max Act: 5.9491. Min Act: -0.1700
Data Index: 2979087 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4804. Min Range: -6.4804
Max Act: 5.9804. Min Act: -0.1700
Data Index: 6949983 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4804. Min Range: -6.4804
Max Act: 5.9491. Min Act: -0.1700
Data Index: 7620182 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4804. Min Range: -6.4804
Max Act: 5.9491. Min Act: -0.1700
Data Index: 3407445 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4804. Min Range: -6.4804
Max Act: 5.9491. Min Act: -0.1700
Data Index: 6425699 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4804. Min Range: -6.4804
Max Act: 5.9491. Min Act: -0.1700
Data Index: 5720052 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4804. Min Range: -6.4804
Max Act: 5.9179. Min Act: -0.1700
Data Index: 2230323 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19