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

Dataset: The Pile

Neuron 4403 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0023. Min Range: -5.0023

Max Act: 5.0023. Min Act: -0.0000

Data Index: 1825526 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 5.0023. Min Range: -5.0023

Max Act: 4.2251. Min Act: -0.0000

Data Index: 203286 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 5.0023. Min Range: -5.0023

Max Act: 4.0532. Min Act: -0.0000

Data Index: 1288722 (The Pile)

Max Activating Token Index: 567

Text #3

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.4617. Min Act: -0.0000

Data Index: 1521885 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.4774. Min Act: -0.0000

Data Index: 205298 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.5828. Min Act: -0.0000

Data Index: 1901741 (The Pile)

Max Activating Token Index: 602

Text #6

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.4053. Min Act: 0.0000

Data Index: 291839 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 5.0023. Min Range: -5.0023

Max Act: 4.0147. Min Act: -0.0000

Data Index: 1719414 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.5342. Min Act: -0.0000

Data Index: 426207 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.3610. Min Act: -0.0000

Data Index: 1875543 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.3535. Min Act: -0.0000

Data Index: 1875302 (The Pile)

Max Activating Token Index: 367

Text #11

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.4187. Min Act: -0.0000

Data Index: 1937879 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.3854. Min Act: -0.0000

Data Index: 338449 (The Pile)

Max Activating Token Index: 270

Text #13

Max Range: 5.0023. Min Range: -5.0023

Max Act: 2.9573. Min Act: -0.0000

Data Index: 1118120 (The Pile)

Max Activating Token Index: 737

Text #14

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.2181. Min Act: -0.0000

Data Index: 662659 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.1510. Min Act: -0.0000

Data Index: 716508 (The Pile)

Max Activating Token Index: 462

Text #16

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.0478. Min Act: -0.0000

Data Index: 1745493 (The Pile)

Max Activating Token Index: 421

Text #17

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.0170. Min Act: -0.0000

Data Index: 1426916 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 5.0023. Min Range: -5.0023

Max Act: 3.2751. Min Act: -0.0000

Data Index: 544278 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 5.0023. Min Range: -5.0023

Max Act: 2.3649. Min Act: -0.0000

Data Index: 1870795 (The Pile)

Max Activating Token Index: 867