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

Dataset: The Pile

Neuron 725 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1499836 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.1830. Min Act: -0.0000

Data Index: 422922 (The Pile)

Max Activating Token Index: 615

Text #2

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9839. Min Act: -0.0000

Data Index: 967235 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9230. Min Act: -0.0000

Data Index: 459878 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1983665 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1811165 (The Pile)

Max Activating Token Index: 203

Text #6

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8603. Min Act: -0.0000

Data Index: 141756 (The Pile)

Max Activating Token Index: 862

Text #7

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1118745 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1917582 (The Pile)

Max Activating Token Index: 352

Text #9

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1848547 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7416. Min Act: -0.0000

Data Index: 291535 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1419009 (The Pile)

Max Activating Token Index: 400

Text #12

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.6891. Min Act: -0.0000

Data Index: 25148 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1393403 (The Pile)

Max Activating Token Index: 410

Text #14

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.6770. Min Act: -0.0000

Data Index: 627433 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1375166 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.6570. Min Act: -0.0000

Data Index: 177261 (The Pile)

Max Activating Token Index: 721

Text #17

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1191759 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.6600. Min Act: -0.0000

Data Index: 45299 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.5881. Min Act: -0.0000

Data Index: 851263 (The Pile)

Max Activating Token Index: 724