Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 655 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1121681 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0383. Min Act: -0.0003

Data Index: 548550 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0378. Min Act: -0.0002

Data Index: 794291 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1015877 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0357. Min Act: -0.0002

Data Index: 757032 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0367. Min Act: -0.0003

Data Index: 317043 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0350. Min Act: -0.0003

Data Index: 150687 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0340. Min Act: -0.0002

Data Index: 13335 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0340. Min Act: -0.0002

Data Index: 441767 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0343. Min Act: -0.0003

Data Index: 181847 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0348. Min Act: -0.0003

Data Index: 781235 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0342. Min Act: -0.0003

Data Index: 592889 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0336. Min Act: -0.0003

Data Index: 551580 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0334. Min Act: -0.0003

Data Index: 156246 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0350. Min Act: -0.0002

Data Index: 673795 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1108674 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0339. Min Act: -0.0003

Data Index: 983549 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0337. Min Act: -0.0003

Data Index: 596914 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1128768 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0336. Min Act: -0.0002

Data Index: 355172 (C4 (Web Text))

Max Activating Token Index: 285