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

Dataset: The Pile

Neuron 1208 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1633120 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9671. Min Act: -0.0000

Data Index: 731288 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8198. Min Act: -0.0000

Data Index: 497863 (The Pile)

Max Activating Token Index: 577

Text #3

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1997699 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0158. Min Act: -0.0000

Data Index: 9626 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1684348 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1581508 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7500. Min Act: -0.0000

Data Index: 546007 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9177. Min Act: -0.0000

Data Index: 117615 (The Pile)

Max Activating Token Index: 784

Text #9

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8564. Min Act: -0.0000

Data Index: 1811029 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1615032 (The Pile)

Max Activating Token Index: 526

Text #11

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8182. Min Act: -0.0000

Data Index: 915951 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1746772 (The Pile)

Max Activating Token Index: 719

Text #13

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1270978 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1045997 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7425. Min Act: -0.0000

Data Index: 425011 (The Pile)

Max Activating Token Index: 696

Text #16

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7019. Min Act: -0.0000

Data Index: 898736 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8299. Min Act: -0.0000

Data Index: 522508 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1820747 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7179. Min Act: -0.0000

Data Index: 834615 (The Pile)

Max Activating Token Index: 498