Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2580 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.9048. Min Act: -0.1700
Data Index: 8043683 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.7797. Min Act: -0.1700
Data Index: 1514970 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.7797. Min Act: -0.1700
Data Index: 5911551 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.6858. Min Act: -0.1700
Data Index: 7588099 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.6702. Min Act: -0.1700
Data Index: 6638854 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.6389. Min Act: -0.1700
Data Index: 6034984 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.5606. Min Act: -0.1700
Data Index: 235766 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.5763. Min Act: -0.1700
Data Index: 4979097 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.5606. Min Act: -0.1700
Data Index: 6815416 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.5763. Min Act: -0.1700
Data Index: 1324940 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.5293. Min Act: -0.1700
Data Index: 3097737 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.5293. Min Act: -0.1700
Data Index: 1166561 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.5293. Min Act: -0.1700
Data Index: 1567275 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.4980. Min Act: -0.1700
Data Index: 898813 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.4980. Min Act: -0.1700
Data Index: 6331633 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.4823. Min Act: -0.1700
Data Index: 253584 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.4510. Min Act: -0.1700
Data Index: 4768741 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.4510. Min Act: -0.1700
Data Index: 569533 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.4353. Min Act: -0.1700
Data Index: 4826150 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9048. Min Range: -3.9048
Max Act: 3.4510. Min Act: -0.1700
Data Index: 2672940 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19