Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5125 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7056. Min Range: -8.7056
Max Act: 8.7056. Min Act: -0.1700
Data Index: 4802486 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7056. Min Range: -8.7056
Max Act: 8.3306. Min Act: -0.1700
Data Index: 6968040 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7056. Min Range: -8.7056
Max Act: 8.1431. Min Act: -0.1700
Data Index: 1558692 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7056. Min Range: -8.7056
Max Act: 8.0806. Min Act: -0.1700
Data Index: 3678019 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7056. Min Range: -8.7056
Max Act: 8.0806. Min Act: -0.1700
Data Index: 7538269 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7056. Min Range: -8.7056
Max Act: 8.0806. Min Act: -0.1700
Data Index: 3221547 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7056. Min Range: -8.7056
Max Act: 8.0181. Min Act: -0.1700
Data Index: 2695211 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.9556. Min Act: -0.1700
Data Index: 842499 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.9244. Min Act: -0.1700
Data Index: 5195598 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.9244. Min Act: -0.1700
Data Index: 3594825 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.9244. Min Act: -0.1700
Data Index: 2948566 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.9244. Min Act: -0.1700
Data Index: 3332562 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.8931. Min Act: -0.1700
Data Index: 1796549 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.8931. Min Act: -0.1700
Data Index: 5785413 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.8931. Min Act: -0.1700
Data Index: 8148156 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.9244. Min Act: -0.1700
Data Index: 137056 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.8931. Min Act: -0.1700
Data Index: 1847781 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.8619. Min Act: -0.1700
Data Index: 2463540 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.8619. Min Act: -0.1700
Data Index: 1053718 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7056. Min Range: -8.7056
Max Act: 7.8619. Min Act: -0.1700
Data Index: 1560986 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19