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

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

Neuron 1554 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1378432 (Python Code)

Max Activating Token Index: 629

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1557247 (Python Code)

Max Activating Token Index: 950

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1401070 (Python Code)

Max Activating Token Index: 877

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1592428 (Python Code)

Max Activating Token Index: 371

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1474920 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1481855 (Python Code)

Max Activating Token Index: 81

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1656241 (Python Code)

Max Activating Token Index: 254

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1399931 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1386305 (Python Code)

Max Activating Token Index: 470

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1561799 (Python Code)

Max Activating Token Index: 864

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0267. Min Act: -0.0002

Data Index: 799545 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1391865 (Python Code)

Max Activating Token Index: 646

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1600004 (Python Code)

Max Activating Token Index: 209

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1593245 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1444278 (Python Code)

Max Activating Token Index: 120

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1380289 (Python Code)

Max Activating Token Index: 241

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1198301 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1399122 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1637462 (Python Code)

Max Activating Token Index: 310

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1653892 (Python Code)

Max Activating Token Index: 204