Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6390 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.8725. Min Act: -0.1700
Data Index: 628074 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.7788. Min Act: -0.1700
Data Index: 3180225 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.7475. Min Act: -0.1700
Data Index: 3688669 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.7475. Min Act: -0.1700
Data Index: 8659880 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.6850. Min Act: -0.1700
Data Index: 4809567 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.6538. Min Act: -0.1700
Data Index: 5002760 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.6850. Min Act: -0.1700
Data Index: 8575626 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.6538. Min Act: -0.1700
Data Index: 8444990 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.6225. Min Act: -0.1700
Data Index: 6802604 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.6225. Min Act: -0.1700
Data Index: 3021364 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.6225. Min Act: -0.1700
Data Index: 1351089 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.5913. Min Act: -0.1700
Data Index: 7089947 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.5600. Min Act: -0.1700
Data Index: 937967 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.5600. Min Act: -0.1700
Data Index: 3782143 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.4975. Min Act: -0.1700
Data Index: 7275002 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.4975. Min Act: -0.1700
Data Index: 5052219 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.4975. Min Act: -0.1700
Data Index: 4099163 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.5288. Min Act: -0.1700
Data Index: 6056698 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.4975. Min Act: -0.1700
Data Index: 7824747 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8725. Min Range: -5.8725
Max Act: 5.4975. Min Act: -0.1700
Data Index: 8043300 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19