Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 87 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7852. Min Range: -6.7852
Max Act: 6.7852. Min Act: -0.1700
Data Index: 6418509 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7852. Min Range: -6.7852
Max Act: 6.7227. Min Act: -0.1700
Data Index: 3658342 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7852. Min Range: -6.7852
Max Act: 6.5977. Min Act: -0.1700
Data Index: 3658341 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7852. Min Range: -6.7852
Max Act: 6.2852. Min Act: -0.1700
Data Index: 632570 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7852. Min Range: -6.7852
Max Act: 6.2540. Min Act: -0.1700
Data Index: 3680007 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7852. Min Range: -6.7852
Max Act: 6.1290. Min Act: -0.1700
Data Index: 1315395 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7852. Min Range: -6.7852
Max Act: 6.0665. Min Act: -0.1700
Data Index: 1346677 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7852. Min Range: -6.7852
Max Act: 6.0352. Min Act: -0.1700
Data Index: 7798378 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7852. Min Range: -6.7852
Max Act: 6.0352. Min Act: -0.1700
Data Index: 5637814 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7852. Min Range: -6.7852
Max Act: 6.0040. Min Act: -0.1700
Data Index: 6628028 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7852. Min Range: -6.7852
Max Act: 6.0352. Min Act: -0.1700
Data Index: 704193 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7852. Min Range: -6.7852
Max Act: 5.9415. Min Act: -0.1700
Data Index: 3783059 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7852. Min Range: -6.7852
Max Act: 5.9727. Min Act: -0.1700
Data Index: 7155564 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7852. Min Range: -6.7852
Max Act: 5.9415. Min Act: -0.1700
Data Index: 1824220 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7852. Min Range: -6.7852
Max Act: 5.9415. Min Act: -0.1700
Data Index: 5773269 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7852. Min Range: -6.7852
Max Act: 5.9415. Min Act: -0.1700
Data Index: 1799699 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7852. Min Range: -6.7852
Max Act: 5.9415. Min Act: -0.1700
Data Index: 6322321 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7852. Min Range: -6.7852
Max Act: 5.9415. Min Act: -0.1700
Data Index: 8054402 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7852. Min Range: -6.7852
Max Act: 5.9102. Min Act: -0.1700
Data Index: 762686 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7852. Min Range: -6.7852
Max Act: 5.9102. Min Act: -0.1700
Data Index: 1809936 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19