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

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

Neuron 5941 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0003

Data Index: 583850 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0283. Min Act: -0.0002

Data Index: 403688 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0279. Min Act: -0.0003

Data Index: 594494 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0270. Min Act: -0.0002

Data Index: 630395 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0248. Min Act: -0.0002

Data Index: 76721 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0244. Min Act: -0.0002

Data Index: 57234 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0229. Min Act: -0.0002

Data Index: 426208 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1469152 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0224. Min Act: -0.0002

Data Index: 813576 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1301372 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0229. Min Act: -0.0002

Data Index: 743115 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0225. Min Act: -0.0002

Data Index: 855336 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0218. Min Act: -0.0003

Data Index: 527779 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0207. Min Act: -0.0002

Data Index: 882359 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0212. Min Act: -0.0002

Data Index: 79307 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1200697 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0215. Min Act: -0.0002

Data Index: 547751 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0216. Min Act: -0.0002

Data Index: 212134 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0215. Min Act: -0.0002

Data Index: 681443 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0211. Min Act: -0.0002

Data Index: 257366 (C4 (Web Text))

Max Activating Token Index: 8