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

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

Neuron 2150 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.8746. Min Act: -0.0000

Data Index: 582321 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.7504. Min Act: -0.0000

Data Index: 165128 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.8325. Min Act: -0.0000

Data Index: 192360 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.9829. Min Act: -0.0000

Data Index: 1104212 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.9398. Min Act: -0.0000

Data Index: 1155737 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.4432. Min Act: -0.0000

Data Index: 405247 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.8170. Min Act: -0.0000

Data Index: 588677 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.7204. Min Act: -0.0000

Data Index: 534592 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.6979. Min Act: -0.0000

Data Index: 1221464 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.8309. Min Act: -0.0000

Data Index: 131113 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.6390. Min Act: -0.0000

Data Index: 1190519 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.6345. Min Act: -0.0000

Data Index: 387395 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.5855. Min Act: -0.0000

Data Index: 358333 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.3625. Min Act: -0.0000

Data Index: 212322 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.3806. Min Act: -0.0000

Data Index: 2689 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.4860. Min Act: -0.0000

Data Index: 479054 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.4887. Min Act: -0.0000

Data Index: 737439 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.6789. Min Act: -0.0000

Data Index: 96535 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.4284. Min Act: -0.0000

Data Index: 333349 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 5.9829. Min Range: -5.9829

Max Act: 5.6421. Min Act: -0.0000

Data Index: 1130261 (C4 (Web Text))

Max Activating Token Index: 325