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

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

Neuron 3290 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0363. Min Act: -0.0000

Data Index: 495136 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0397. Min Act: -0.0000

Data Index: 244497 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0351. Min Act: -0.0000

Data Index: 517336 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0385. Min Act: -0.0000

Data Index: 650402 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0315. Min Act: -0.0000

Data Index: 1247071 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1304240 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0326. Min Act: -0.0000

Data Index: 213524 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0336. Min Act: -0.0000

Data Index: 16646 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1559716 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1551031 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0340. Min Act: -0.0000

Data Index: 330714 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1111072 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1253736 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0313. Min Act: -0.0000

Data Index: 737203 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0300. Min Act: -0.0000

Data Index: 268422 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0321. Min Act: -0.0000

Data Index: 537591 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0310. Min Act: -0.0000

Data Index: 330414 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0319. Min Act: -0.0000

Data Index: 913906 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0341. Min Act: -0.0000

Data Index: 893509 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0304. Min Act: -0.0000

Data Index: 1194371 (C4 (Web Text))

Max Activating Token Index: 949