Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0725. Min Range: -7.0725
Max Act: 7.0725. Min Act: -0.1700
Data Index: 4922922 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.7912. Min Act: -0.1700
Data Index: 2710429 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.7912. Min Act: -0.1700
Data Index: 6274814 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.7600. Min Act: -0.1700
Data Index: 3731259 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.6975. Min Act: -0.1700
Data Index: 2262070 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.6975. Min Act: -0.1700
Data Index: 80755 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.6975. Min Act: -0.1700
Data Index: 7047484 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.6975. Min Act: -0.1700
Data Index: 17408 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.6350. Min Act: -0.1700
Data Index: 1024002 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.6037. Min Act: -0.1700
Data Index: 5680691 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.5412. Min Act: -0.1700
Data Index: 1403569 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.5725. Min Act: -0.1700
Data Index: 1505753 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.5412. Min Act: -0.1700
Data Index: 8009282 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.5412. Min Act: -0.1700
Data Index: 7242227 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.5100. Min Act: -0.1700
Data Index: 400736 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.5100. Min Act: -0.1700
Data Index: 6648868 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.5100. Min Act: -0.1700
Data Index: 2228063 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.5100. Min Act: -0.1700
Data Index: 3317375 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.5100. Min Act: -0.1700
Data Index: 2292980 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.4787. Min Act: -0.1700
Data Index: 356717 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19