Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3587 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.8565. Min Act: -0.0000

Data Index: 16029 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1044889 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.7675. Min Act: -0.0001

Data Index: 1476612 (The Pile)

Max Activating Token Index: 895

Text #3

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1026709 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.7280. Min Act: -0.0000

Data Index: 165285 (The Pile)

Max Activating Token Index: 527

Text #5

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.7512. Min Act: -0.0000

Data Index: 557849 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.7209. Min Act: -0.0000

Data Index: 490711 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.7459. Min Act: -0.0001

Data Index: 1306388 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6670. Min Act: -0.0000

Data Index: 225870 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6704. Min Act: -0.0000

Data Index: 272891 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.7003. Min Act: -0.0001

Data Index: 160550 (The Pile)

Max Activating Token Index: 138

Text #11

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6627. Min Act: -0.0000

Data Index: 973476 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1552819 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6413. Min Act: -0.0000

Data Index: 942540 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.5731. Min Act: -0.0000

Data Index: 306795 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1414464 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1878092 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6308. Min Act: -0.0000

Data Index: 202932 (The Pile)

Max Activating Token Index: 774

Text #18

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1747584 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 0.8565. Min Range: -0.8565

Max Act: 0.6235. Min Act: -0.0000

Data Index: 772491 (The Pile)

Max Activating Token Index: 104