Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0977. Min Range: -6.0977
Max Act: 6.0977. Min Act: -0.1700
Data Index: 8657103 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.9727. Min Act: -0.1700
Data Index: 7586751 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.9414. Min Act: -0.1700
Data Index: 5526662 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8789. Min Act: -0.1700
Data Index: 3606732 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8789. Min Act: -0.1700
Data Index: 4243709 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8164. Min Act: -0.1700
Data Index: 7093254 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8164. Min Act: -0.1700
Data Index: 2527291 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.7852. Min Act: -0.1700
Data Index: 57073 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.7852. Min Act: -0.1700
Data Index: 8698487 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.7227. Min Act: -0.1700
Data Index: 99949 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.7227. Min Act: -0.1700
Data Index: 6543643 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.6914. Min Act: -0.1700
Data Index: 224173 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.6914. Min Act: -0.1700
Data Index: 7292757 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.7227. Min Act: -0.1700
Data Index: 5906538 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.6602. Min Act: -0.1700
Data Index: 3795333 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.6289. Min Act: -0.1700
Data Index: 6929612 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.6289. Min Act: -0.1700
Data Index: 8424443 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.5977. Min Act: -0.1700
Data Index: 3075629 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.5664. Min Act: -0.1700
Data Index: 3515968 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.5664. Min Act: -0.1700
Data Index: 5264200 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19