Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4118 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6759. Min Range: -9.6759
Max Act: 9.6759. Min Act: -0.1700
Data Index: 8643044 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6759. Min Range: -9.6759
Max Act: 9.6134. Min Act: -0.1700
Data Index: 1919665 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6759. Min Range: -9.6759
Max Act: 9.3634. Min Act: -0.1700
Data Index: 4827991 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6759. Min Range: -9.6759
Max Act: 9.3009. Min Act: -0.1700
Data Index: 4406601 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6759. Min Range: -9.6759
Max Act: 9.2384. Min Act: -0.1700
Data Index: 7536435 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6759. Min Range: -9.6759
Max Act: 9.1759. Min Act: -0.1700
Data Index: 1368236 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6759. Min Range: -9.6759
Max Act: 9.1134. Min Act: -0.1700
Data Index: 1224425 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6759. Min Range: -9.6759
Max Act: 8.9884. Min Act: -0.1700
Data Index: 8304389 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6759. Min Range: -9.6759
Max Act: 9.0509. Min Act: -0.1700
Data Index: 754967 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6759. Min Range: -9.6759
Max Act: 9.0509. Min Act: -0.1700
Data Index: 7192592 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6759. Min Range: -9.6759
Max Act: 9.0509. Min Act: -0.1700
Data Index: 3857113 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6759. Min Range: -9.6759
Max Act: 9.0509. Min Act: -0.1700
Data Index: 5858793 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6759. Min Range: -9.6759
Max Act: 8.9259. Min Act: -0.1700
Data Index: 5043145 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6759. Min Range: -9.6759
Max Act: 8.8009. Min Act: -0.1700
Data Index: 4013740 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6759. Min Range: -9.6759
Max Act: 8.8009. Min Act: -0.1700
Data Index: 5002387 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6759. Min Range: -9.6759
Max Act: 8.7384. Min Act: -0.1700
Data Index: 4986370 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6759. Min Range: -9.6759
Max Act: 8.7384. Min Act: -0.1700
Data Index: 5500446 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6759. Min Range: -9.6759
Max Act: 8.7384. Min Act: -0.1700
Data Index: 5535235 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6759. Min Range: -9.6759
Max Act: 8.7384. Min Act: -0.1700
Data Index: 2682359 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6759. Min Range: -9.6759
Max Act: 8.7384. Min Act: -0.1700
Data Index: 824691 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19