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

Dataset: The Pile

Neuron 1312 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: 3.2292. Min Range: -3.2292

Max Act: 3.1592. Min Act: -0.0000

Data Index: 828108 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 3.2292. Min Range: -3.2292

Max Act: 3.2292. Min Act: -0.0000

Data Index: 1805187 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.7483. Min Act: -0.0000

Data Index: 1779510 (The Pile)

Max Activating Token Index: 896

Text #3

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.0472. Min Act: -0.0000

Data Index: 335127 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.9199. Min Act: -0.0000

Data Index: 613638 (The Pile)

Max Activating Token Index: 18

Text #5

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.9010. Min Act: -0.0000

Data Index: 310151 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.1097. Min Act: -0.0000

Data Index: 542138 (The Pile)

Max Activating Token Index: 974

Text #7

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.9471. Min Act: -0.0000

Data Index: 1736888 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.7893. Min Act: -0.0000

Data Index: 1468660 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.7657. Min Act: -0.0000

Data Index: 1334419 (The Pile)

Max Activating Token Index: 788

Text #10

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.7450. Min Act: -0.0000

Data Index: 1371314 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.7335. Min Act: -0.0000

Data Index: 1957724 (The Pile)

Max Activating Token Index: 628

Text #12

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.8235. Min Act: -0.0000

Data Index: 66899 (The Pile)

Max Activating Token Index: 441

Text #13

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.7078. Min Act: -0.0000

Data Index: 7372 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1094462 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.7197. Min Act: -0.0000

Data Index: 799728 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.7015. Min Act: -0.0000

Data Index: 1066165 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.6064. Min Act: -0.0000

Data Index: 1749008 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.6877. Min Act: -0.0000

Data Index: 23209 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 3.2292. Min Range: -3.2292

Max Act: 1.6885. Min Act: -0.0000

Data Index: 1779513 (The Pile)

Max Activating Token Index: 18