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

Dataset: The Pile

Neuron 2210 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: 1.7386. Min Range: -1.7386

Max Act: 1.7386. Min Act: -0.0000

Data Index: 1217212 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.4157. Min Act: -0.0000

Data Index: 416522 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.3311. Min Act: -0.0000

Data Index: 587648 (The Pile)

Max Activating Token Index: 872

Text #3

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.2714. Min Act: -0.0000

Data Index: 443767 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.3692. Min Act: -0.0000

Data Index: 762092 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.4052. Min Act: -0.0000

Data Index: 1671276 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.2628. Min Act: -0.0000

Data Index: 905714 (The Pile)

Max Activating Token Index: 870

Text #7

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.2809. Min Act: -0.0000

Data Index: 1495377 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.3599. Min Act: -0.0000

Data Index: 1864693 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.2265. Min Act: -0.0000

Data Index: 1346686 (The Pile)

Max Activating Token Index: 891

Text #10

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1312990 (The Pile)

Max Activating Token Index: 743

Text #11

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1232511 (The Pile)

Max Activating Token Index: 820

Text #12

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.1255. Min Act: -0.0000

Data Index: 268474 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.2178. Min Act: -0.0000

Data Index: 197868 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.1912. Min Act: -0.0000

Data Index: 601288 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.1793. Min Act: -0.0000

Data Index: 1067832 (The Pile)

Max Activating Token Index: 437

Text #16

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.1877. Min Act: -0.0000

Data Index: 1724292 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.1175. Min Act: -0.0000

Data Index: 34203 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1822831 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 1.7386. Min Range: -1.7386

Max Act: 1.1352. Min Act: -0.0000

Data Index: 849707 (The Pile)

Max Activating Token Index: 938