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

Dataset: The Pile

Neuron 3937 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: 0.7421. Min Range: -0.7421

Max Act: 0.7421. Min Act: -0.0000

Data Index: 569415 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.7045. Min Act: -0.0000

Data Index: 577418 (The Pile)

Max Activating Token Index: 338

Text #2

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1182012 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6524. Min Act: -0.0000

Data Index: 221223 (The Pile)

Max Activating Token Index: 570

Text #4

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1540444 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1816659 (The Pile)

Max Activating Token Index: 750

Text #6

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1925027 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6676. Min Act: -0.0000

Data Index: 605749 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6692. Min Act: -0.0000

Data Index: 906670 (The Pile)

Max Activating Token Index: 868

Text #9

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6828. Min Act: -0.0000

Data Index: 551188 (The Pile)

Max Activating Token Index: 369

Text #10

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1311631 (The Pile)

Max Activating Token Index: 788

Text #11

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1354344 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1893609 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1575545 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.5505. Min Act: -0.0000

Data Index: 28989 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1672981 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6221. Min Act: -0.0000

Data Index: 514583 (The Pile)

Max Activating Token Index: 586

Text #17

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1301568 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1720299 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 0.7421. Min Range: -0.7421

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1546574 (The Pile)

Max Activating Token Index: 921