Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 998 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1099757 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1237912 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1210047 (The Pile)

Max Activating Token Index: 548

Text #3

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8244. Min Act: -0.0000

Data Index: 1704619 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1552539 (The Pile)

Max Activating Token Index: 401

Text #5

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1914119 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1050519 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8165. Min Act: -0.0000

Data Index: 982479 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1692889 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7513. Min Act: 0.0000

Data Index: 551413 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1667909 (The Pile)

Max Activating Token Index: 665

Text #11

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7461. Min Act: -0.0000

Data Index: 793512 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7257. Min Act: 0.0000

Data Index: 1867600 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7299. Min Act: -0.0000

Data Index: 312347 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7044. Min Act: -0.0000

Data Index: 922701 (The Pile)

Max Activating Token Index: 455

Text #15

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7042. Min Act: 0.0000

Data Index: 222310 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1724297 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7478. Min Act: -0.0000

Data Index: 146074 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1771383 (The Pile)

Max Activating Token Index: 32

Text #19

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.6973. Min Act: -0.0000

Data Index: 336430 (The Pile)

Max Activating Token Index: 627