Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 667 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.5792. Min Act: -0.1700
Data Index: 5912813 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.5792. Min Act: -0.1700
Data Index: 2953747 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.5792. Min Act: -0.1700
Data Index: 2361334 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.5479. Min Act: -0.1700
Data Index: 4865641 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.5479. Min Act: -0.1700
Data Index: 809924 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.5479. Min Act: -0.1700
Data Index: 4717850 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.5165. Min Act: -0.1700
Data Index: 5169624 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4852. Min Act: -0.1700
Data Index: 3769786 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4852. Min Act: -0.1700
Data Index: 7588060 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4852. Min Act: -0.1700
Data Index: 8753863 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4852. Min Act: -0.1700
Data Index: 5783806 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4852. Min Act: -0.1700
Data Index: 431875 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4852. Min Act: -0.1700
Data Index: 8095048 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4852. Min Act: -0.1700
Data Index: 7833550 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4539. Min Act: -0.1700
Data Index: 4105324 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4539. Min Act: -0.1700
Data Index: 1763766 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4539. Min Act: -0.1700
Data Index: 2558485 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4539. Min Act: -0.1700
Data Index: 4928973 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4539. Min Act: -0.1700
Data Index: 417367 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5792. Min Range: -3.5792
Max Act: 3.4539. Min Act: -0.1700
Data Index: 5490742 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19