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

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

Neuron 4741 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: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1551 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0507. Min Act: -0.0002

Data Index: 789681 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0521. Min Act: -0.0002

Data Index: 660187 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1233234 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1473660 (Python Code)

Max Activating Token Index: 530

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0516. Min Act: -0.0002

Data Index: 941805 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0299. Min Act: -0.0002

Data Index: 31384 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0487. Min Act: -0.0002

Data Index: 463336 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0403. Min Act: -0.0002

Data Index: 216888 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1297698 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0417. Min Act: -0.0002

Data Index: 859854 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0314. Min Act: -0.0002

Data Index: 830617 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1336993 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0431. Min Act: -0.0002

Data Index: 958059 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0470. Min Act: -0.0002

Data Index: 629895 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0370. Min Act: -0.0002

Data Index: 568574 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0355. Min Act: -0.0002

Data Index: 2739 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0380. Min Act: -0.0002

Data Index: 23401 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0329. Min Act: -0.0002

Data Index: 29277 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1339448 (C4 (Web Text))

Max Activating Token Index: 106