Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1048 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.6504. Min Act: -0.1700
Data Index: 6177354 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.6504. Min Act: -0.1700
Data Index: 5468291 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.5879. Min Act: -0.1700
Data Index: 4630132 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.5254. Min Act: -0.1700
Data Index: 5464312 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.3379. Min Act: -0.1700
Data Index: 1479705 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.3379. Min Act: -0.1700
Data Index: 5432900 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.2754. Min Act: -0.1700
Data Index: 6836445 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.2754. Min Act: -0.1700
Data Index: 5457198 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.2129. Min Act: -0.1700
Data Index: 4519002 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.2129. Min Act: -0.1700
Data Index: 5863572 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.2129. Min Act: -0.1700
Data Index: 3523997 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.2129. Min Act: -0.1700
Data Index: 6778331 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.2129. Min Act: -0.1700
Data Index: 513635 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.1504. Min Act: -0.1700
Data Index: 5897822 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.0254. Min Act: -0.1700
Data Index: 328613 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.1504. Min Act: -0.1700
Data Index: 513634 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.0879. Min Act: -0.1700
Data Index: 1674099 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.0879. Min Act: -0.1700
Data Index: 8216545 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.0879. Min Act: -0.1700
Data Index: 3879572 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6504. Min Range: -9.6504
Max Act: 9.1504. Min Act: -0.1700
Data Index: 2591024 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19