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

Dataset: The Pile

Neuron 2085 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1000512 (The Pile)

Max Activating Token Index: 319

Text #1

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1829176 (The Pile)

Max Activating Token Index: 740

Text #2

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7740. Min Act: -0.0000

Data Index: 1241917 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1317282 (The Pile)

Max Activating Token Index: 124

Text #4

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1933242 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1487528 (The Pile)

Max Activating Token Index: 966

Text #6

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7349. Min Act: -0.0000

Data Index: 821254 (The Pile)

Max Activating Token Index: 783

Text #7

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1467340 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1341595 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1426909 (The Pile)

Max Activating Token Index: 711

Text #10

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1039076 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7444. Min Act: -0.0000

Data Index: 42717 (The Pile)

Max Activating Token Index: 740

Text #12

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1490342 (The Pile)

Max Activating Token Index: 828

Text #13

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7050. Min Act: -0.0000

Data Index: 769959 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1332451 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6699. Min Act: -0.0000

Data Index: 697500 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7075. Min Act: -0.0000

Data Index: 239307 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1857897 (The Pile)

Max Activating Token Index: 742

Text #18

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6578. Min Act: -0.0000

Data Index: 56161 (The Pile)

Max Activating Token Index: 788

Text #19

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6785. Min Act: -0.0000

Data Index: 726238 (The Pile)

Max Activating Token Index: 1018