Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 829 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.6181. Min Act: -0.1700
Data Index: 5177694 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.4931. Min Act: -0.1700
Data Index: 274354 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.4618. Min Act: -0.1700
Data Index: 6825724 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.3681. Min Act: -0.1700
Data Index: 658643 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.3368. Min Act: -0.1700
Data Index: 2820034 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.3368. Min Act: -0.1700
Data Index: 5256546 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.3368. Min Act: -0.1700
Data Index: 2203487 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.3056. Min Act: -0.1700
Data Index: 3181185 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.3056. Min Act: -0.1700
Data Index: 3316704 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.3056. Min Act: -0.1700
Data Index: 6918407 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.3056. Min Act: -0.1700
Data Index: 4071903 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.2743. Min Act: -0.1700
Data Index: 4377939 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.2743. Min Act: -0.1700
Data Index: 5302012 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.2743. Min Act: -0.1700
Data Index: 8494507 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.2430. Min Act: -0.1700
Data Index: 7234279 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.2118. Min Act: -0.1700
Data Index: 743018 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.2430. Min Act: -0.1700
Data Index: 2057273 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.2430. Min Act: -0.1700
Data Index: 5825912 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.2430. Min Act: -0.1700
Data Index: 6781634 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6181. Min Range: -4.6181
Max Act: 4.2430. Min Act: -0.1700
Data Index: 945518 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19