Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3856 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5001. Min Range: -10.5001
Max Act: 10.5001. Min Act: -0.1700
Data Index: 2731379 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5001. Min Range: -10.5001
Max Act: 10.2501. Min Act: -0.1700
Data Index: 1363426 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5001. Min Range: -10.5001
Max Act: 10.2501. Min Act: -0.1700
Data Index: 4557324 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5001. Min Range: -10.5001
Max Act: 10.1251. Min Act: -0.1700
Data Index: 4654136 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.9376. Min Act: -0.1700
Data Index: 8369749 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5001. Min Range: -10.5001
Max Act: 10.0001. Min Act: -0.1700
Data Index: 7680113 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5001. Min Range: -10.5001
Max Act: 10.0001. Min Act: -0.1700
Data Index: 5709276 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5001. Min Range: -10.5001
Max Act: 10.0001. Min Act: -0.1700
Data Index: 5547110 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5001. Min Range: -10.5001
Max Act: 10.0001. Min Act: -0.1700
Data Index: 6831535 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.9376. Min Act: -0.1700
Data Index: 6841377 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.9376. Min Act: -0.1700
Data Index: 1482711 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.8751. Min Act: -0.1700
Data Index: 1154901 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.9376. Min Act: -0.1700
Data Index: 391788 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.9376. Min Act: -0.1700
Data Index: 7884423 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.9376. Min Act: -0.1700
Data Index: 2682112 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.8751. Min Act: -0.1700
Data Index: 3763120 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.8751. Min Act: -0.1700
Data Index: 7552302 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.8751. Min Act: -0.1700
Data Index: 8500357 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.8751. Min Act: -0.1700
Data Index: 1293232 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5001. Min Range: -10.5001
Max Act: 9.8126. Min Act: -0.1700
Data Index: 7673489 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19