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

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

Neuron 1796 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1079433 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1029694 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1252593 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1254816 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1203085 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1239511 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0338. Min Act: -0.0003

Data Index: 5781 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0338. Min Act: -0.0003

Data Index: 619872 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0341. Min Act: -0.0003

Data Index: 205615 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0324. Min Act: -0.0003

Data Index: 447453 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1413895 (Python Code)

Max Activating Token Index: 386

Text #11

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0317. Min Act: -0.0003

Data Index: 915464 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0320. Min Act: -0.0002

Data Index: 808765 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1008643 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1627018 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0331. Min Act: -0.0003

Data Index: 517427 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0324. Min Act: -0.0003

Data Index: 296207 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0321. Min Act: -0.0003

Data Index: 586518 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0321. Min Act: -0.0003

Data Index: 533813 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0322. Min Act: -0.0003

Data Index: 20914 (C4 (Web Text))

Max Activating Token Index: 420