Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5089 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.8248. Min Act: -0.0001

Data Index: 74681 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7256. Min Act: -0.0001

Data Index: 1289346 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.6684. Min Act: -0.0000

Data Index: 398349 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5660. Min Act: -0.0001

Data Index: 139365 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5571. Min Act: -0.0001

Data Index: 97038 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4898. Min Act: -0.0001

Data Index: 641356 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5281. Min Act: -0.0001

Data Index: 424659 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1083606 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5139. Min Act: -0.0000

Data Index: 317311 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4653. Min Act: -0.0001

Data Index: 693953 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4712. Min Act: -0.0000

Data Index: 224367 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1221716 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4182. Min Act: -0.0001

Data Index: 562745 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4309. Min Act: -0.0000

Data Index: 840582 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4569. Min Act: -0.0001

Data Index: 302348 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4679. Min Act: -0.0001

Data Index: 679010 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4564. Min Act: -0.0001

Data Index: 120122 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5251. Min Act: -0.0001

Data Index: 482565 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4786. Min Act: -0.0001

Data Index: 557503 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4482. Min Act: -0.0001

Data Index: 110919 (C4 (Web Text))

Max Activating Token Index: 196