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

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

Neuron 333 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1310. Min Act: -0.0002

Data Index: 1216730 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0821. Min Act: -0.0002

Data Index: 669138 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0781. Min Act: -0.0002

Data Index: 459877 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0758. Min Act: -0.0002

Data Index: 923866 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0765. Min Act: -0.0002

Data Index: 554640 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1255440 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1263658 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0663. Min Act: -0.0002

Data Index: 30813 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0663. Min Act: -0.0002

Data Index: 774085 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0635. Min Act: -0.0002

Data Index: 103202 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1235984 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0633. Min Act: -0.0002

Data Index: 86035 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1186351 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0612. Min Act: -0.0002

Data Index: 882232 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0605. Min Act: -0.0002

Data Index: 12557 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1071320 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0598. Min Act: -0.0002

Data Index: 705829 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1275921 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0565. Min Act: -0.0002

Data Index: 364062 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0564. Min Act: -0.0002

Data Index: 622573 (C4 (Web Text))

Max Activating Token Index: 218