Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4620 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.9798. Min Act: -0.1700
Data Index: 5065091 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.9486. Min Act: -0.1700
Data Index: 8216042 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.7766. Min Act: -0.1700
Data Index: 4768084 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.8235. Min Act: -0.1700
Data Index: 8686794 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.7453. Min Act: -0.1700
Data Index: 4410828 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.6827. Min Act: -0.1700
Data Index: 743975 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.6515. Min Act: -0.1700
Data Index: 7601078 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.6515. Min Act: -0.1700
Data Index: 2232919 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.6358. Min Act: -0.1700
Data Index: 1789808 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.6202. Min Act: -0.1700
Data Index: 1941509 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.6202. Min Act: -0.1700
Data Index: 1376145 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.5889. Min Act: -0.1700
Data Index: 396117 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.5732. Min Act: -0.1700
Data Index: 2928896 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.5575. Min Act: -0.1700
Data Index: 6905425 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.5732. Min Act: -0.1700
Data Index: 3376411 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.5419. Min Act: -0.1700
Data Index: 4552001 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.5419. Min Act: -0.1700
Data Index: 8787582 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.5419. Min Act: -0.1700
Data Index: 1829092 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.5106. Min Act: -0.1700
Data Index: 1982418 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9798. Min Range: -3.9798
Max Act: 3.5262. Min Act: -0.1700
Data Index: 5464885 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19