Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4460 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.7930. Min Act: -0.1700
Data Index: 4699794 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.7452. Min Act: -0.1700
Data Index: 7339625 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.7132. Min Act: -0.1700
Data Index: 4104389 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.7132. Min Act: -0.1699
Data Index: 6334665 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6972. Min Act: -0.1700
Data Index: 5273697 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6972. Min Act: -0.1700
Data Index: 3149102 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6812. Min Act: -0.1700
Data Index: 8513047 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6812. Min Act: -0.1697
Data Index: 6414290 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6812. Min Act: -0.1699
Data Index: 5974282 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6652. Min Act: -0.1700
Data Index: 5310008 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6652. Min Act: -0.1693
Data Index: 8122815 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6652. Min Act: -0.1695
Data Index: 2326480 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6652. Min Act: -0.1700
Data Index: 2574027 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6492. Min Act: -0.1699
Data Index: 1175790 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6652. Min Act: -0.1700
Data Index: 7817388 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6492. Min Act: -0.1700
Data Index: 2807026 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6492. Min Act: -0.1700
Data Index: 2233564 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6492. Min Act: -0.1681
Data Index: 2826266 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6331. Min Act: -0.1700
Data Index: 5508271 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7930. Min Range: -2.7930
Max Act: 2.6492. Min Act: -0.1700
Data Index: 273999 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19