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

Dataset: The Pile

Neuron 3528 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1818454 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1336777 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1578715 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3679. Min Act: 0.0000

Data Index: 328369 (The Pile)

Max Activating Token Index: 201

Text #4

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3550. Min Act: -0.0000

Data Index: 242728 (The Pile)

Max Activating Token Index: 150

Text #5

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1586489 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3686. Min Act: -0.0000

Data Index: 436627 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1693197 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1886016 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3534. Min Act: -0.0000

Data Index: 227006 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3320. Min Act: -0.0000

Data Index: 692837 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3577. Min Act: -0.0000

Data Index: 354740 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3222. Min Act: -0.0000

Data Index: 689444 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3583. Min Act: -0.0000

Data Index: 724693 (The Pile)

Max Activating Token Index: 747

Text #14

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1612782 (The Pile)

Max Activating Token Index: 872

Text #15

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1650907 (The Pile)

Max Activating Token Index: 527

Text #16

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1682803 (The Pile)

Max Activating Token Index: 796

Text #17

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1917014 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.2842. Min Act: -0.0000

Data Index: 151824 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.2935. Min Act: 0.0002

Data Index: 880071 (The Pile)

Max Activating Token Index: 212