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

Dataset: The Pile

Neuron 1892 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: 0.5459. Min Range: -0.5459

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1913216 (The Pile)

Max Activating Token Index: 319

Text #1

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1913226 (The Pile)

Max Activating Token Index: 355

Text #2

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1779560 (The Pile)

Max Activating Token Index: 607

Text #3

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4607. Min Act: 0.0000

Data Index: 719023 (The Pile)

Max Activating Token Index: 582

Text #4

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1137825 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1431962 (The Pile)

Max Activating Token Index: 785

Text #6

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1841453 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3631. Min Act: -0.0000

Data Index: 804969 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3518. Min Act: -0.0000

Data Index: 769093 (The Pile)

Max Activating Token Index: 725

Text #9

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1278326 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3670. Min Act: -0.0000

Data Index: 165584 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1327142 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1858235 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1745761 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1707706 (The Pile)

Max Activating Token Index: 963

Text #15

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3561. Min Act: -0.0000

Data Index: 378406 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1301332 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3204. Min Act: 0.0000

Data Index: 736579 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3260. Min Act: -0.0000

Data Index: 358854 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3006. Min Act: -0.0000

Data Index: 1213358 (The Pile)

Max Activating Token Index: 408