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

Dataset: The Pile

Neuron 3897 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: 0.5002. Min Range: -0.5002

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1190767 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4776. Min Act: -0.0000

Data Index: 51078 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1564295 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1502569 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1100272 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3948. Min Act: -0.0000

Data Index: 109339 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1425202 (The Pile)

Max Activating Token Index: 1020

Text #7

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1905371 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1707053 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1576373 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3710. Min Act: -0.0000

Data Index: 862252 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3860. Min Act: -0.0000

Data Index: 921179 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3609. Min Act: -0.0000

Data Index: 144658 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1420163 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1338541 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3503. Min Act: -0.0000

Data Index: 322875 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3221. Min Act: -0.0000

Data Index: 183808 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3508. Min Act: -0.0000

Data Index: 506545 (The Pile)

Max Activating Token Index: 212

Text #18

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3063. Min Act: -0.0000

Data Index: 664378 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1483329 (The Pile)

Max Activating Token Index: 379