Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4196 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.4778. Min Act: -0.1700
Data Index: 2584355 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.4465. Min Act: -0.1700
Data Index: 5069946 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.4152. Min Act: -0.1700
Data Index: 5816434 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3840. Min Act: -0.1700
Data Index: 2025063 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3840. Min Act: -0.1700
Data Index: 4502479 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3527. Min Act: -0.1700
Data Index: 3560118 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3527. Min Act: -0.1700
Data Index: 5259147 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3527. Min Act: -0.1700
Data Index: 7574696 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3840. Min Act: -0.1700
Data Index: 7289743 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3527. Min Act: -0.1699
Data Index: 1506765 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3527. Min Act: -0.1700
Data Index: 1425534 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3527. Min Act: -0.1700
Data Index: 4471910 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3215. Min Act: -0.1700
Data Index: 1373885 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3215. Min Act: -0.1700
Data Index: 2152763 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3215. Min Act: -0.1700
Data Index: 2002106 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.2902. Min Act: -0.1700
Data Index: 7629572 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.3215. Min Act: -0.1700
Data Index: 6236013 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.2902. Min Act: -0.1700
Data Index: 3232451 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.2902. Min Act: -0.1700
Data Index: 960037 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4778. Min Range: -4.4778
Max Act: 4.2902. Min Act: -0.1700
Data Index: 3806490 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19