Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0430. Min Range: -5.0430
Max Act: 5.0430. Min Act: -0.1700
Data Index: 4393351 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.9805. Min Act: -0.1700
Data Index: 4945480 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.9180. Min Act: -0.1700
Data Index: 788503 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.8868. Min Act: -0.1700
Data Index: 822097 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.8868. Min Act: -0.1700
Data Index: 4092116 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.8243. Min Act: -0.1700
Data Index: 4792368 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.8243. Min Act: -0.1700
Data Index: 1851770 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.7930. Min Act: -0.1700
Data Index: 4616936 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.8243. Min Act: -0.1700
Data Index: 6235493 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.7930. Min Act: -0.1700
Data Index: 1645564 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.7930. Min Act: -0.1700
Data Index: 4601195 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.7618. Min Act: -0.1700
Data Index: 83428 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.7618. Min Act: -0.1700
Data Index: 8729876 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.6993. Min Act: -0.1700
Data Index: 6481603 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.7305. Min Act: -0.1700
Data Index: 413458 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.7305. Min Act: -0.1700
Data Index: 3957268 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.7305. Min Act: -0.1700
Data Index: 8726309 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.6680. Min Act: -0.1700
Data Index: 2555454 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.6993. Min Act: -0.1700
Data Index: 5916593 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0430. Min Range: -5.0430
Max Act: 4.6993. Min Act: -0.1700
Data Index: 2176129 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19