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

Dataset: The Pile

Neuron 4324 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1589188 (The Pile)

Max Activating Token Index: 949

Text #1

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.3264. Min Act: -0.0000

Data Index: 1661073 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1999593 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.9258. Min Act: -0.0000

Data Index: 242349 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1241828 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.8611. Min Act: -0.0000

Data Index: 484630 (The Pile)

Max Activating Token Index: 472

Text #6

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1560001 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.6503. Min Act: -0.0000

Data Index: 755627 (The Pile)

Max Activating Token Index: 882

Text #8

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.6263. Min Act: -0.0000

Data Index: 843827 (The Pile)

Max Activating Token Index: 934

Text #9

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.6482. Min Act: -0.0000

Data Index: 75645 (The Pile)

Max Activating Token Index: 451

Text #10

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.6386. Min Act: -0.0000

Data Index: 958266 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1561370 (The Pile)

Max Activating Token Index: 554

Text #12

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.5846. Min Act: -0.0000

Data Index: 683719 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1898595 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1132881 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1666019 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.5686. Min Act: -0.0000

Data Index: 365136 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.5730. Min Act: -0.0000

Data Index: 747055 (The Pile)

Max Activating Token Index: 830

Text #18

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1646167 (The Pile)

Max Activating Token Index: 289

Text #19

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1727445 (The Pile)

Max Activating Token Index: 560