Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4156 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.9599. Min Act: -0.1700
Data Index: 8095992 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.9599. Min Act: -0.1700
Data Index: 875434 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.8974. Min Act: -0.1700
Data Index: 8347972 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.8974. Min Act: -0.1700
Data Index: 7236873 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.8349. Min Act: -0.1700
Data Index: 4862622 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.8349. Min Act: -0.1700
Data Index: 1523817 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.7099. Min Act: -0.1700
Data Index: 144752 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.7724. Min Act: -0.1700
Data Index: 4373948 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.7724. Min Act: -0.1700
Data Index: 2579764 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.7099. Min Act: -0.1700
Data Index: 8187446 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.7099. Min Act: -0.1700
Data Index: 1151904 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.5849. Min Act: -0.1700
Data Index: 3650272 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.6474. Min Act: -0.1700
Data Index: 576876 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.5849. Min Act: -0.1700
Data Index: 3919633 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.5849. Min Act: -0.1700
Data Index: 2222403 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.5849. Min Act: -0.1700
Data Index: 3387305 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.6474. Min Act: -0.1700
Data Index: 6532088 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.5849. Min Act: -0.1700
Data Index: 1397347 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.5849. Min Act: -0.1700
Data Index: 7247106 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9599. Min Range: -9.9599
Max Act: 9.5224. Min Act: -0.1700
Data Index: 1384227 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19