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

Dataset: The Pile

Neuron 3139 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: 0.8429. Min Range: -0.8429

Max Act: 0.7742. Min Act: -0.0000

Data Index: 742296 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1273192 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1585853 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.8075. Min Act: -0.0000

Data Index: 713505 (The Pile)

Max Activating Token Index: 350

Text #4

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1055966 (The Pile)

Max Activating Token Index: 866

Text #5

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1442061 (The Pile)

Max Activating Token Index: 309

Text #6

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.6427. Min Act: -0.0000

Data Index: 27390 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.6464. Min Act: -0.0000

Data Index: 831071 (The Pile)

Max Activating Token Index: 11

Text #8

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.6412. Min Act: -0.0000

Data Index: 208496 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1715183 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1002409 (The Pile)

Max Activating Token Index: 372

Text #11

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1818625 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5293. Min Act: -0.0000

Data Index: 476572 (The Pile)

Max Activating Token Index: 211

Text #13

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1875744 (The Pile)

Max Activating Token Index: 378

Text #14

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1199959 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1438697 (The Pile)

Max Activating Token Index: 234

Text #16

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5330. Min Act: -0.0000

Data Index: 760796 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5100. Min Act: -0.0000

Data Index: 566337 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5006. Min Act: -0.0000

Data Index: 571537 (The Pile)

Max Activating Token Index: 322

Text #19

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1302796 (The Pile)

Max Activating Token Index: 745