Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4388 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1446385 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9101. Min Act: -0.0000

Data Index: 556022 (The Pile)

Max Activating Token Index: 449

Text #2

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1988692 (The Pile)

Max Activating Token Index: 6

Text #3

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1638082 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1307934 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8216. Min Act: -0.0000

Data Index: 778508 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1253880 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1730784 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7947. Min Act: -0.0000

Data Index: 836493 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1916768 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7755. Min Act: -0.0000

Data Index: 326491 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1884573 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7789. Min Act: -0.0000

Data Index: 535163 (The Pile)

Max Activating Token Index: 475

Text #13

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7707. Min Act: -0.0000

Data Index: 186012 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7770. Min Act: -0.0000

Data Index: 774846 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7655. Min Act: -0.0000

Data Index: 876558 (The Pile)

Max Activating Token Index: 939

Text #16

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1907824 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7882. Min Act: -0.0000

Data Index: 338592 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.6971. Min Act: -0.0000

Data Index: 93034 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1352287 (The Pile)

Max Activating Token Index: 356