Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.1725. Min Act: -0.1700
Data Index: 824893 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.1392. Min Act: -0.1700
Data Index: 2749813 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.1392. Min Act: -0.1700
Data Index: 7283521 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.1225. Min Act: -0.1700
Data Index: 5693556 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.0891. Min Act: -0.1700
Data Index: 6123568 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.1058. Min Act: -0.1700
Data Index: 5953974 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.1225. Min Act: -0.1700
Data Index: 8600126 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.0891. Min Act: -0.1700
Data Index: 7396806 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.1058. Min Act: -0.1700
Data Index: 4967447 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.1058. Min Act: -0.1700
Data Index: 2558547 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.1058. Min Act: -0.1700
Data Index: 5826299 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.1058. Min Act: -0.1700
Data Index: 1549357 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.1058. Min Act: -0.1700
Data Index: 5107342 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.0723. Min Act: -0.1700
Data Index: 450791 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.0891. Min Act: -0.1700
Data Index: 7136903 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.0891. Min Act: -0.1700
Data Index: 7136896 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.0891. Min Act: -0.1700
Data Index: 8298343 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.0387. Min Act: -0.1700
Data Index: 8284039 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.0555. Min Act: -0.1700
Data Index: 7062294 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1725. Min Range: -2.1725
Max Act: 2.0387. Min Act: -0.1700
Data Index: 7101263 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19