Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2942 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3338. Min Range: -8.3338
Max Act: 8.3338. Min Act: -0.1700
Data Index: 8638749 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3338. Min Range: -8.3338
Max Act: 8.2401. Min Act: -0.1700
Data Index: 8158796 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.9901. Min Act: -0.1700
Data Index: 6748735 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.9901. Min Act: -0.1700
Data Index: 3775194 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.9588. Min Act: -0.1700
Data Index: 6936082 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.9588. Min Act: -0.1700
Data Index: 4364578 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.9588. Min Act: -0.1700
Data Index: 6170599 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.9588. Min Act: -0.1700
Data Index: 7695844 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.9276. Min Act: -0.1700
Data Index: 2384296 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8963. Min Act: -0.1700
Data Index: 574464 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8651. Min Act: -0.1700
Data Index: 1874668 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8651. Min Act: -0.1700
Data Index: 2303927 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8651. Min Act: -0.1700
Data Index: 4008511 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8338. Min Act: -0.1700
Data Index: 7268750 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8026. Min Act: -0.1700
Data Index: 5690758 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.7713. Min Act: -0.1700
Data Index: 3457010 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.7713. Min Act: -0.1700
Data Index: 7894211 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8026. Min Act: -0.1700
Data Index: 3929026 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8026. Min Act: -0.1700
Data Index: 5592469 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8338. Min Act: -0.1700
Data Index: 7549137 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19