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

Dataset: The Pile

Neuron 5086 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1605. Min Act: -0.0000

Data Index: 1305221 (The Pile)

Max Activating Token Index: 861

Text #1

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1556. Min Act: -0.0000

Data Index: 456417 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1487. Min Act: -0.0000

Data Index: 902102 (The Pile)

Max Activating Token Index: 285

Text #3

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1399. Min Act: -0.0000

Data Index: 865731 (The Pile)

Max Activating Token Index: 746

Text #4

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1618073 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1409426 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1009356 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1301. Min Act: -0.0000

Data Index: 1251718 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1314. Min Act: -0.0000

Data Index: 1526665 (The Pile)

Max Activating Token Index: 939

Text #9

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1248. Min Act: -0.0000

Data Index: 702220 (The Pile)

Max Activating Token Index: 233

Text #10

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1300590 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1613826 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1205. Min Act: -0.0000

Data Index: 462958 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1608848 (The Pile)

Max Activating Token Index: 360

Text #14

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1175. Min Act: -0.0000

Data Index: 628243 (The Pile)

Max Activating Token Index: 891

Text #15

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1337. Min Act: -0.0000

Data Index: 663754 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1308454 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1231. Min Act: -0.0000

Data Index: 531763 (The Pile)

Max Activating Token Index: 168

Text #18

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1488417 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1436424 (The Pile)

Max Activating Token Index: 758