Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1191 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1753. Min Act: -0.0001

Data Index: 177966 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1735. Min Act: -0.0001

Data Index: 926848 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1599. Min Act: -0.0001

Data Index: 684443 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1221511 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1443. Min Act: -0.0002

Data Index: 988087 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1449. Min Act: -0.0002

Data Index: 742460 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1434. Min Act: -0.0001

Data Index: 449578 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1267. Min Act: -0.0001

Data Index: 867099 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1073406 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1300. Min Act: -0.0001

Data Index: 833895 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1455. Min Act: -0.0001

Data Index: 291039 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1166. Min Act: -0.0001

Data Index: 438489 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1314. Min Act: -0.0001

Data Index: 796662 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1262. Min Act: -0.0002

Data Index: 142592 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1364. Min Act: -0.0001

Data Index: 66285 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1291. Min Act: -0.0001

Data Index: 100514 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1237. Min Act: -0.0002

Data Index: 579332 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1257. Min Act: -0.0002

Data Index: 803203 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1397. Min Act: -0.0001

Data Index: 1146385 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1251. Min Act: -0.0001

Data Index: 395169 (C4 (Web Text))

Max Activating Token Index: 496