Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6068 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0768. Min Range: -6.0768
Max Act: 6.0768. Min Act: -0.1700
Data Index: 2236552 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0768. Min Range: -6.0768
Max Act: 6.0455. Min Act: -0.1700
Data Index: 2173520 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.9830. Min Act: -0.1700
Data Index: 5863368 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.9518. Min Act: -0.1700
Data Index: 7040615 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.9518. Min Act: -0.1700
Data Index: 306014 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.9205. Min Act: -0.1700
Data Index: 8437914 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.9205. Min Act: -0.1700
Data Index: 5431055 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.8893. Min Act: -0.1700
Data Index: 1074740 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.8580. Min Act: -0.1700
Data Index: 8754561 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.7955. Min Act: -0.1700
Data Index: 7940370 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.7955. Min Act: -0.1700
Data Index: 6072509 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.7955. Min Act: -0.1700
Data Index: 3273055 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.7955. Min Act: -0.1700
Data Index: 1810826 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.7955. Min Act: -0.1700
Data Index: 4286545 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.7955. Min Act: -0.1700
Data Index: 1990967 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.7330. Min Act: -0.1700
Data Index: 4473915 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.7643. Min Act: -0.1700
Data Index: 7382518 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.7643. Min Act: -0.1700
Data Index: 3104713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.7330. Min Act: -0.1700
Data Index: 4797369 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0768. Min Range: -6.0768
Max Act: 5.7330. Min Act: -0.1700
Data Index: 6863961 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19