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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3699 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.5625. Min Act: -0.0003

Data Index: 1126298 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.5474. Min Act: -0.0003

Data Index: 359817 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.5103. Min Act: -0.0003

Data Index: 655960 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4986. Min Act: -0.0003

Data Index: 1248864 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4606. Min Act: -0.0003

Data Index: 829010 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4564. Min Act: -0.0003

Data Index: 1061707 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4536. Min Act: -0.0003

Data Index: 353234 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4622. Min Act: -0.0003

Data Index: 961612 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4393. Min Act: -0.0003

Data Index: 76300 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4392. Min Act: -0.0002

Data Index: 801123 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4388. Min Act: -0.0003

Data Index: 1112650 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4321. Min Act: -0.0003

Data Index: 670058 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4275. Min Act: -0.0003

Data Index: 816139 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4407. Min Act: -0.0003

Data Index: 1219659 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4251. Min Act: -0.0003

Data Index: 575254 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4247. Min Act: -0.0002

Data Index: 565123 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4089. Min Act: -0.0003

Data Index: 549514 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4198. Min Act: -0.0003

Data Index: 427852 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4147. Min Act: -0.0003

Data Index: 131625 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4150. Min Act: -0.0003

Data Index: 899559 (C4 (Web Text))

Max Activating Token Index: 979