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

Dataset: The Pile

Neuron 4348 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: 0.8078. Min Range: -0.8078

Max Act: 0.8078. Min Act: -0.0000

Data Index: 984773 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.7606. Min Act: -0.0000

Data Index: 470370 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.7442. Min Act: -0.0000

Data Index: 784395 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6449. Min Act: -0.0000

Data Index: 221631 (The Pile)

Max Activating Token Index: 298

Text #4

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6226. Min Act: 0.0000

Data Index: 182610 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6012. Min Act: -0.0000

Data Index: 573806 (The Pile)

Max Activating Token Index: 910

Text #6

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1135715 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.4669. Min Act: -0.0000

Data Index: 586862 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1453015 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5584. Min Act: -0.0000

Data Index: 639860 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5885. Min Act: -0.0000

Data Index: 880181 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5945. Min Act: -0.0000

Data Index: 391476 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1685662 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1962461 (The Pile)

Max Activating Token Index: 987

Text #14

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5106. Min Act: -0.0000

Data Index: 315793 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1556107 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.4867. Min Act: -0.0000

Data Index: 1368390 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1422797 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.4657. Min Act: -0.0000

Data Index: 509223 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.4711. Min Act: -0.0000

Data Index: 662118 (The Pile)

Max Activating Token Index: 591