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

Dataset: The Pile

Neuron 2517 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: 0.8368. Min Range: -0.8368

Max Act: 0.8368. Min Act: -0.0000

Data Index: 767312 (The Pile)

Max Activating Token Index: 53

Text #1

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.7100. Min Act: -0.0000

Data Index: 592265 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6772. Min Act: -0.0000

Data Index: 547668 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6831. Min Act: -0.0000

Data Index: 168309 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1549068 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6447. Min Act: -0.0000

Data Index: 281291 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6588. Min Act: -0.0000

Data Index: 114338 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1824488 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1048863 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6544. Min Act: -0.0000

Data Index: 674528 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1474900 (The Pile)

Max Activating Token Index: 959

Text #11

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1124454 (The Pile)

Max Activating Token Index: 596

Text #12

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6222. Min Act: -0.0000

Data Index: 14836 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1966629 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1866654 (The Pile)

Max Activating Token Index: 1006

Text #15

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1350018 (The Pile)

Max Activating Token Index: 122

Text #16

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1096199 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.5784. Min Act: -0.0000

Data Index: 600898 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1705541 (The Pile)

Max Activating Token Index: 133

Text #19

Max Range: 0.8368. Min Range: -0.8368

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1631281 (The Pile)

Max Activating Token Index: 795