Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7062. Min Range: -7.7062
Max Act: 7.7062. Min Act: -0.1700
Data Index: 4989415 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7062. Min Range: -7.7062
Max Act: 7.6437. Min Act: -0.1700
Data Index: 7742052 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7062. Min Range: -7.7062
Max Act: 7.5812. Min Act: -0.1700
Data Index: 254841 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7062. Min Range: -7.7062
Max Act: 7.5187. Min Act: -0.1700
Data Index: 3036321 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7062. Min Range: -7.7062
Max Act: 7.5187. Min Act: -0.1700
Data Index: 7687542 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7062. Min Range: -7.7062
Max Act: 7.5187. Min Act: -0.1700
Data Index: 6238759 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7062. Min Range: -7.7062
Max Act: 7.5187. Min Act: -0.1700
Data Index: 3314530 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7062. Min Range: -7.7062
Max Act: 7.4250. Min Act: -0.1700
Data Index: 3870732 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7062. Min Range: -7.7062
Max Act: 7.3000. Min Act: -0.1700
Data Index: 2481748 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7062. Min Range: -7.7062
Max Act: 6.9875. Min Act: -0.1700
Data Index: 4542695 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7062. Min Range: -7.7062
Max Act: 6.9875. Min Act: -0.1700
Data Index: 3036324 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7062. Min Range: -7.7062
Max Act: 6.9875. Min Act: -0.1700
Data Index: 2535734 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7062. Min Range: -7.7062
Max Act: 6.9875. Min Act: -0.1700
Data Index: 1672432 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7062. Min Range: -7.7062
Max Act: 6.9562. Min Act: -0.1700
Data Index: 66001 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7062. Min Range: -7.7062
Max Act: 6.9250. Min Act: -0.1700
Data Index: 2568244 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7062. Min Range: -7.7062
Max Act: 6.8000. Min Act: -0.1700
Data Index: 7169951 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7062. Min Range: -7.7062
Max Act: 6.7687. Min Act: -0.1700
Data Index: 1119368 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7062. Min Range: -7.7062
Max Act: 6.5812. Min Act: -0.1700
Data Index: 1107925 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7062. Min Range: -7.7062
Max Act: 6.4875. Min Act: -0.1700
Data Index: 2963881 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7062. Min Range: -7.7062
Max Act: 6.5187. Min Act: -0.1700
Data Index: 4848586 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19