Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4307 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.5238. Min Act: -0.1700
Data Index: 5480569 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.5238. Min Act: -0.1700
Data Index: 3856320 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.3676. Min Act: -0.1700
Data Index: 1243399 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.3988. Min Act: -0.1700
Data Index: 3922261 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.3363. Min Act: -0.1700
Data Index: 6245350 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.3051. Min Act: -0.1700
Data Index: 8050874 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.2738. Min Act: -0.1700
Data Index: 8194734 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.2738. Min Act: -0.1700
Data Index: 7284917 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.2738. Min Act: -0.1700
Data Index: 6268866 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.2426. Min Act: -0.1700
Data Index: 7298809 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.2113. Min Act: -0.1700
Data Index: 1881717 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.1801. Min Act: -0.1700
Data Index: 5792043 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.1801. Min Act: -0.1700
Data Index: 7181870 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.1488. Min Act: -0.1700
Data Index: 7179509 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.1176. Min Act: -0.1700
Data Index: 4911850 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.0551. Min Act: -0.1700
Data Index: 3427972 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.0238. Min Act: -0.1700
Data Index: 5905073 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.0238. Min Act: -0.1700
Data Index: 2966759 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5238. Min Range: -7.5238
Max Act: 6.9926. Min Act: -0.1700
Data Index: 7336357 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5238. Min Range: -7.5238
Max Act: 7.0238. Min Act: -0.1700
Data Index: 1962442 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19