Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4725 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1744. Min Range: -6.1744
Max Act: 6.1744. Min Act: -0.1700
Data Index: 266037 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1744. Min Range: -6.1744
Max Act: 6.1432. Min Act: -0.1700
Data Index: 265274 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1744. Min Range: -6.1744
Max Act: 6.0807. Min Act: -0.1700
Data Index: 1084917 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1744. Min Range: -6.1744
Max Act: 6.0182. Min Act: -0.1700
Data Index: 2039509 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1744. Min Range: -6.1744
Max Act: 6.0182. Min Act: -0.1700
Data Index: 3953052 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8932. Min Act: -0.1700
Data Index: 2481796 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.9244. Min Act: -0.1700
Data Index: 7762765 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8932. Min Act: -0.1700
Data Index: 1702849 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8619. Min Act: -0.1700
Data Index: 6949555 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8619. Min Act: -0.1700
Data Index: 3718433 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8619. Min Act: -0.1700
Data Index: 6364066 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8619. Min Act: -0.1700
Data Index: 1586532 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8307. Min Act: -0.1700
Data Index: 4168394 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8307. Min Act: -0.1700
Data Index: 7805015 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8619. Min Act: -0.1700
Data Index: 7826750 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8307. Min Act: -0.1700
Data Index: 605024 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8307. Min Act: -0.1700
Data Index: 5922298 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8307. Min Act: -0.1700
Data Index: 3985098 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8307. Min Act: -0.1700
Data Index: 55679 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1744. Min Range: -6.1744
Max Act: 5.8307. Min Act: -0.1700
Data Index: 7826752 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19