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

Dataset: The Pile

Neuron 3466 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.7426. Min Act: -0.0000

Data Index: 1068219 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.1113. Min Act: -0.0000

Data Index: 690283 (The Pile)

Max Activating Token Index: 586

Text #2

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.2359. Min Act: -0.0000

Data Index: 309458 (The Pile)

Max Activating Token Index: 319

Text #3

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.4379. Min Act: -0.0000

Data Index: 51219 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.4348. Min Act: -0.0000

Data Index: 131734 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.8162. Min Act: -0.0000

Data Index: 1420025 (The Pile)

Max Activating Token Index: 74

Text #6

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.9413. Min Act: -0.0000

Data Index: 655484 (The Pile)

Max Activating Token Index: 214

Text #7

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.7919. Min Act: -0.0000

Data Index: 1994391 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.7593. Min Act: -0.0000

Data Index: 1022630 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.8975. Min Act: -0.0000

Data Index: 1220875 (The Pile)

Max Activating Token Index: 371

Text #10

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.7027. Min Act: -0.0000

Data Index: 1776503 (The Pile)

Max Activating Token Index: 426

Text #11

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.6405. Min Act: -0.0000

Data Index: 1005456 (The Pile)

Max Activating Token Index: 803

Text #12

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.4578. Min Act: -0.0000

Data Index: 1462808 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.5363. Min Act: -0.0000

Data Index: 344408 (The Pile)

Max Activating Token Index: 887

Text #14

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.8928. Min Act: -0.0000

Data Index: 1610386 (The Pile)

Max Activating Token Index: 624

Text #15

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.8088. Min Act: -0.0000

Data Index: 1798748 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.7799. Min Act: -0.0000

Data Index: 580085 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.2252. Min Act: -0.0000

Data Index: 1552453 (The Pile)

Max Activating Token Index: 410

Text #18

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.5922. Min Act: -0.0000

Data Index: 1312072 (The Pile)

Max Activating Token Index: 777

Text #19

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.3186. Min Act: -0.0000

Data Index: 970425 (The Pile)

Max Activating Token Index: 308