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

Dataset: The Pile

Neuron 3060 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.8506. Min Act: -0.0000

Data Index: 191631 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7917. Min Act: 0.0000

Data Index: 1358934 (The Pile)

Max Activating Token Index: 393

Text #2

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7974. Min Act: -0.0000

Data Index: 350415 (The Pile)

Max Activating Token Index: 317

Text #3

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.8123. Min Act: -0.0000

Data Index: 147467 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1743978 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1710779 (The Pile)

Max Activating Token Index: 914

Text #6

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1523094 (The Pile)

Max Activating Token Index: 533

Text #7

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6728. Min Act: 0.0000

Data Index: 225707 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6284. Min Act: -0.0000

Data Index: 874106 (The Pile)

Max Activating Token Index: 331

Text #9

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1861704 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1719845 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6248. Min Act: -0.0000

Data Index: 43164 (The Pile)

Max Activating Token Index: 471

Text #12

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1393402 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6092. Min Act: 0.0000

Data Index: 1855605 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5937. Min Act: 0.0000

Data Index: 735643 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6789. Min Act: -0.0000

Data Index: 372192 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5649. Min Act: -0.0000

Data Index: 256812 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.4983. Min Act: 0.0000

Data Index: 246599 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5473. Min Act: 0.0000

Data Index: 1823271 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5476. Min Act: 0.0000

Data Index: 935513 (The Pile)

Max Activating Token Index: 469