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

Dataset: The Pile

Neuron 2258 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: 0.6883. Min Range: -0.6883

Max Act: 0.6883. Min Act: -0.0000

Data Index: 622573 (The Pile)

Max Activating Token Index: 588

Text #1

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6486. Min Act: -0.0000

Data Index: 761521 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.6169. Min Act: -0.0000

Data Index: 76562 (The Pile)

Max Activating Token Index: 693

Text #3

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5991. Min Act: -0.0000

Data Index: 259446 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5623. Min Act: -0.0000

Data Index: 20139 (The Pile)

Max Activating Token Index: 458

Text #5

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1474021 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1623318 (The Pile)

Max Activating Token Index: 608

Text #7

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1745194 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1358456 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.5104. Min Act: -0.0000

Data Index: 500508 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.4582. Min Act: -0.0000

Data Index: 165627 (The Pile)

Max Activating Token Index: 576

Text #11

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.4674. Min Act: 0.0000

Data Index: 1291088 (The Pile)

Max Activating Token Index: 684

Text #12

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1340198 (The Pile)

Max Activating Token Index: 412

Text #13

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1572880 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.4807. Min Act: -0.0000

Data Index: 340362 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1912647 (The Pile)

Max Activating Token Index: 295

Text #16

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1397213 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1721110 (The Pile)

Max Activating Token Index: 997

Text #18

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1552077 (The Pile)

Max Activating Token Index: 282

Text #19

Max Range: 0.6883. Min Range: -0.6883

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1274973 (The Pile)

Max Activating Token Index: 218