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

Dataset: The Pile

Neuron 2863 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: 1.0342. Min Range: -1.0342

Max Act: 1.0342. Min Act: -0.0000

Data Index: 194142 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.9671. Min Act: -0.0000

Data Index: 544742 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.9497. Min Act: 0.0000

Data Index: 652962 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.8107. Min Act: -0.0000

Data Index: 461886 (The Pile)

Max Activating Token Index: 313

Text #4

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.8292. Min Act: 0.0000

Data Index: 345543 (The Pile)

Max Activating Token Index: 203

Text #5

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6971. Min Act: -0.0000

Data Index: 146097 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1347967 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6949. Min Act: -0.0000

Data Index: 319529 (The Pile)

Max Activating Token Index: 811

Text #8

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1802099 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.7359. Min Act: -0.0000

Data Index: 862026 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.7238. Min Act: -0.0000

Data Index: 99783 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1810605 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1232871 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6924. Min Act: -0.0000

Data Index: 13857 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.7142. Min Act: -0.0000

Data Index: 528081 (The Pile)

Max Activating Token Index: 712

Text #15

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1394457 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1478618 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6986. Min Act: 0.0000

Data Index: 1857308 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1625552 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1296072 (The Pile)

Max Activating Token Index: 621