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

Dataset: The Pile

Neuron 37 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1289315 (The Pile)

Max Activating Token Index: 390

Text #1

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7952. Min Act: -0.0000

Data Index: 520393 (The Pile)

Max Activating Token Index: 449

Text #2

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6999. Min Act: -0.0000

Data Index: 774262 (The Pile)

Max Activating Token Index: 916

Text #3

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1842990 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1596303 (The Pile)

Max Activating Token Index: 14

Text #5

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7177. Min Act: -0.0000

Data Index: 599671 (The Pile)

Max Activating Token Index: 201

Text #6

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7330. Min Act: -0.0000

Data Index: 360421 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6843. Min Act: -0.0000

Data Index: 701084 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7076. Min Act: -0.0000

Data Index: 577686 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1499492 (The Pile)

Max Activating Token Index: 220

Text #10

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6577. Min Act: -0.0000

Data Index: 379893 (The Pile)

Max Activating Token Index: 240

Text #11

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1778267 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6702. Min Act: -0.0000

Data Index: 758864 (The Pile)

Max Activating Token Index: 144

Text #13

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6758. Min Act: -0.0000

Data Index: 249383 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6386. Min Act: -0.0000

Data Index: 466378 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6354. Min Act: -0.0000

Data Index: 394262 (The Pile)

Max Activating Token Index: 665

Text #16

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6648. Min Act: -0.0000

Data Index: 652322 (The Pile)

Max Activating Token Index: 180

Text #17

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1365319 (The Pile)

Max Activating Token Index: 927

Text #18

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1914120 (The Pile)

Max Activating Token Index: 828

Text #19

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1277002 (The Pile)

Max Activating Token Index: 831