Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2017 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0005

Data Index: 174704 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0303. Min Act: -0.0005

Data Index: 181714 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0290. Min Act: -0.0005

Data Index: 1001199 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0282. Min Act: -0.0005

Data Index: 1125507 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0271. Min Act: -0.0005

Data Index: 50586 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0273. Min Act: -0.0005

Data Index: 554389 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0272. Min Act: -0.0005

Data Index: 1574901 (Python Code)

Max Activating Token Index: 676

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0291. Min Act: -0.0005

Data Index: 446621 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0269. Min Act: -0.0005

Data Index: 690102 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0283. Min Act: -0.0005

Data Index: 985696 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0271. Min Act: -0.0005

Data Index: 129903 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0268. Min Act: -0.0005

Data Index: 1496971 (Python Code)

Max Activating Token Index: 717

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0265. Min Act: -0.0005

Data Index: 181783 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0249. Min Act: -0.0005

Data Index: 1039581 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0265. Min Act: -0.0005

Data Index: 166760 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0255. Min Act: -0.0005

Data Index: 1257220 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0250. Min Act: -0.0005

Data Index: 1324878 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0255. Min Act: -0.0005

Data Index: 1321347 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0252. Min Act: -0.0005

Data Index: 428101 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0250. Min Act: -0.0005

Data Index: 197381 (C4 (Web Text))

Max Activating Token Index: 717