Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5751 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.7590. Min Act: -0.1700
Data Index: 7851732 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6182. Min Act: -0.1700
Data Index: 2071947 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6182. Min Act: -0.1700
Data Index: 5820515 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5869. Min Act: -0.1700
Data Index: 2198576 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6026. Min Act: -0.1700
Data Index: 912012 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5713. Min Act: -0.1700
Data Index: 3543364 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5869. Min Act: -0.1700
Data Index: 8372192 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5713. Min Act: -0.1700
Data Index: 5592292 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5556. Min Act: -0.1700
Data Index: 1630268 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5713. Min Act: -0.1700
Data Index: 4105314 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5400. Min Act: -0.1700
Data Index: 4442826 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5086. Min Act: -0.1700
Data Index: 519699 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5086. Min Act: -0.1700
Data Index: 5694755 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.4930. Min Act: -0.1700
Data Index: 557339 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.4930. Min Act: -0.1700
Data Index: 15535 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.4930. Min Act: -0.1700
Data Index: 3047077 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.4930. Min Act: -0.1700
Data Index: 1060373 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.4773. Min Act: -0.1700
Data Index: 3493699 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.4773. Min Act: -0.1700
Data Index: 6352104 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.4616. Min Act: -0.1700
Data Index: 7995343 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19