Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3372 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.4493. Min Act: -0.1700
Data Index: 1036382 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.4493. Min Act: -0.1700
Data Index: 8618423 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.4493. Min Act: -0.1700
Data Index: 5778790 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.4181. Min Act: -0.1700
Data Index: 1379388 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.4493. Min Act: -0.1700
Data Index: 3098365 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.3868. Min Act: -0.1700
Data Index: 2766722 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.3868. Min Act: -0.1700
Data Index: 2535417 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.3556. Min Act: -0.1700
Data Index: 4142609 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.2931. Min Act: -0.1700
Data Index: 7478840 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.3243. Min Act: -0.1700
Data Index: 7949194 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.2931. Min Act: -0.1700
Data Index: 1332716 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.2931. Min Act: -0.1700
Data Index: 7743737 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.2306. Min Act: -0.1700
Data Index: 3770562 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.2618. Min Act: -0.1700
Data Index: 947758 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.2618. Min Act: -0.1700
Data Index: 2860477 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.2306. Min Act: -0.1700
Data Index: 7628534 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.2306. Min Act: -0.1700
Data Index: 5765108 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.2306. Min Act: -0.1700
Data Index: 6491607 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.1993. Min Act: -0.1700
Data Index: 5891718 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4493. Min Range: -5.4493
Max Act: 5.1993. Min Act: -0.1700
Data Index: 5918180 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19