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

Dataset: The Pile

Neuron 262 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9719. Min Act: -0.0000

Data Index: 390882 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1608710 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.6672. Min Act: -0.0000

Data Index: 1102411 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.5033. Min Act: -0.0000

Data Index: 307378 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4887. Min Act: -0.0000

Data Index: 1247972 (The Pile)

Max Activating Token Index: 686

Text #5

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1742419 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3626. Min Act: -0.0000

Data Index: 611174 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1936661 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.2228. Min Act: -0.0000

Data Index: 836229 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.2259. Min Act: -0.0000

Data Index: 583980 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.1358. Min Act: -0.0000

Data Index: 204126 (The Pile)

Max Activating Token Index: 743

Text #11

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.1755. Min Act: -0.0000

Data Index: 1416855 (The Pile)

Max Activating Token Index: 554

Text #12

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.0607. Min Act: -0.0000

Data Index: 839687 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.1195. Min Act: -0.0000

Data Index: 972301 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.0405. Min Act: -0.0000

Data Index: 713732 (The Pile)

Max Activating Token Index: 189

Text #15

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.1610. Min Act: -0.0000

Data Index: 138369 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 1.9719. Min Range: -1.9719

Max Act: 0.9640. Min Act: -0.0000

Data Index: 378506 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.0758. Min Act: -0.0000

Data Index: 1721945 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1470957 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.1296. Min Act: -0.0000

Data Index: 104819 (The Pile)

Max Activating Token Index: 500