Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3462 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.7016. Min Act: -0.1700
Data Index: 1774025 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.5766. Min Act: -0.1700
Data Index: 1774031 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.5453. Min Act: -0.1700
Data Index: 5139094 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.3890. Min Act: -0.1700
Data Index: 1452017 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.3890. Min Act: -0.1700
Data Index: 1774030 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.3265. Min Act: -0.1700
Data Index: 7750787 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.3265. Min Act: -0.1700
Data Index: 5688757 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.3265. Min Act: -0.1700
Data Index: 8710971 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.3265. Min Act: -0.1700
Data Index: 4958333 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.2953. Min Act: -0.1700
Data Index: 993010 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.2953. Min Act: -0.1700
Data Index: 5938889 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.2953. Min Act: -0.1700
Data Index: 4353901 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.2640. Min Act: -0.1700
Data Index: 5927541 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.2328. Min Act: -0.1700
Data Index: 7579466 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.2953. Min Act: -0.1700
Data Index: 4205338 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.2640. Min Act: -0.1700
Data Index: 4840023 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.2328. Min Act: -0.1700
Data Index: 5070928 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.2328. Min Act: -0.1700
Data Index: 4746349 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.2328. Min Act: -0.1700
Data Index: 452352 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7016. Min Range: -4.7016
Max Act: 4.2015. Min Act: -0.1700
Data Index: 3811680 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19