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

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

Neuron 803 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0875. Min Act: -0.0000

Data Index: 212109 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0684. Min Act: -0.0000

Data Index: 737321 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0702. Min Act: -0.0000

Data Index: 656835 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0619. Min Act: -0.0000

Data Index: 702322 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0596. Min Act: -0.0000

Data Index: 668661 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0564. Min Act: -0.0000

Data Index: 1178245 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0560. Min Act: -0.0000

Data Index: 269764 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0547. Min Act: -0.0000

Data Index: 107844 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0522. Min Act: -0.0000

Data Index: 897269 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0536. Min Act: -0.0000

Data Index: 143001 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0570. Min Act: -0.0000

Data Index: 576189 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1129035 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0480. Min Act: -0.0001

Data Index: 774645 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1121983 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0489. Min Act: -0.0000

Data Index: 139265 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0492. Min Act: -0.0000

Data Index: 1247366 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0503. Min Act: -0.0000

Data Index: 695046 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0480. Min Act: -0.0000

Data Index: 639195 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0524. Min Act: -0.0000

Data Index: 913773 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0487. Min Act: -0.0001

Data Index: 712135 (C4 (Web Text))

Max Activating Token Index: 951