Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4669 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5116. Min Range: -9.5116
Max Act: 9.5116. Min Act: -0.1700
Data Index: 6546467 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5116. Min Range: -9.5116
Max Act: 9.3241. Min Act: -0.1700
Data Index: 7680910 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.8241. Min Act: -0.1700
Data Index: 7015731 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.7616. Min Act: -0.1700
Data Index: 5690463 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.6991. Min Act: -0.1700
Data Index: 996021 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.5116. Min Act: -0.1700
Data Index: 3546829 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.5116. Min Act: -0.1700
Data Index: 456575 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.5116. Min Act: -0.1700
Data Index: 649496 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.5116. Min Act: -0.1700
Data Index: 3207211 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.4491. Min Act: -0.1700
Data Index: 2417382 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.4491. Min Act: -0.1700
Data Index: 4303566 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.3553. Min Act: -0.1700
Data Index: 1673282 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.3241. Min Act: -0.1700
Data Index: 423106 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.2928. Min Act: -0.1700
Data Index: 1927285 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.2616. Min Act: -0.1700
Data Index: 4779582 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.2303. Min Act: -0.1700
Data Index: 5949158 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.2303. Min Act: -0.1700
Data Index: 6401994 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.2303. Min Act: -0.1700
Data Index: 1288606 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.2303. Min Act: -0.1700
Data Index: 1687357 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5116. Min Range: -9.5116
Max Act: 8.1991. Min Act: -0.1700
Data Index: 1662547 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19