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

Dataset: The Pile

Neuron 650 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1436341 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1970043 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1618155 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5542. Min Act: -0.0000

Data Index: 142286 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5030. Min Act: -0.0000

Data Index: 282226 (The Pile)

Max Activating Token Index: 28

Text #5

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5393. Min Act: -0.0000

Data Index: 792185 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1606065 (The Pile)

Max Activating Token Index: 382

Text #7

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1082473 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4878. Min Act: -0.0000

Data Index: 15530 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1539498 (The Pile)

Max Activating Token Index: 581

Text #10

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1552163 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1407428 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1785937 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4679. Min Act: -0.0000

Data Index: 756126 (The Pile)

Max Activating Token Index: 170

Text #14

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1042024 (The Pile)

Max Activating Token Index: 84

Text #15

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1663974 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4262. Min Act: -0.0000

Data Index: 84373 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1817935 (The Pile)

Max Activating Token Index: 459

Text #18

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1546262 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4210. Min Act: -0.0000

Data Index: 305204 (The Pile)

Max Activating Token Index: 423