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

Dataset: The Pile

Neuron 1605 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: 0.6386. Min Range: -0.6386

Max Act: 0.6361. Min Act: -0.0000

Data Index: 481843 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6386. Min Act: -0.0000

Data Index: 423151 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1584796 (The Pile)

Max Activating Token Index: 497

Text #3

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1950795 (The Pile)

Max Activating Token Index: 870

Text #4

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6094. Min Act: -0.0000

Data Index: 188591 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6014. Min Act: -0.0000

Data Index: 821919 (The Pile)

Max Activating Token Index: 656

Text #6

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5615. Min Act: -0.0000

Data Index: 295943 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5303. Min Act: -0.0000

Data Index: 90414 (The Pile)

Max Activating Token Index: 561

Text #8

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1554878 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1334342 (The Pile)

Max Activating Token Index: 826

Text #10

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1866952 (The Pile)

Max Activating Token Index: 351

Text #11

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5455. Min Act: -0.0000

Data Index: 443839 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5542. Min Act: -0.0000

Data Index: 133125 (The Pile)

Max Activating Token Index: 901

Text #13

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5374. Min Act: -0.0000

Data Index: 279157 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5505. Min Act: -0.0000

Data Index: 393947 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1800362 (The Pile)

Max Activating Token Index: 364

Text #16

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1880023 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1278449 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5256. Min Act: -0.0000

Data Index: 157296 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5115. Min Act: -0.0000

Data Index: 743401 (The Pile)

Max Activating Token Index: 260