Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4805 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.8106. Min Act: -0.1700
Data Index: 4116625 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.8106. Min Act: -0.1700
Data Index: 7913929 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.7628. Min Act: -0.1700
Data Index: 7131261 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.7309. Min Act: -0.1700
Data Index: 2908844 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6989. Min Act: -0.1700
Data Index: 7935265 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.7149. Min Act: -0.1700
Data Index: 7127841 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.7309. Min Act: -0.1700
Data Index: 6706015 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6829. Min Act: -0.1700
Data Index: 961981 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6989. Min Act: -0.1700
Data Index: 5869575 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6989. Min Act: -0.1700
Data Index: 7958329 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6829. Min Act: -0.1700
Data Index: 887731 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6829. Min Act: -0.1700
Data Index: 2757804 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6829. Min Act: -0.1700
Data Index: 2935277 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6669. Min Act: -0.1700
Data Index: 5075422 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6669. Min Act: -0.1700
Data Index: 4389462 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6669. Min Act: -0.1700
Data Index: 6362031 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6508. Min Act: -0.1700
Data Index: 5041793 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6508. Min Act: -0.1700
Data Index: 2202759 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6669. Min Act: -0.1700
Data Index: 4570903 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8106. Min Range: -2.8106
Max Act: 2.6669. Min Act: -0.1700
Data Index: 2919636 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19