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

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

Neuron 3157 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: 0.0770. Min Range: -0.0770

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1570386 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1360466 (Python Code)

Max Activating Token Index: 121

Text #2

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0656. Min Act: -0.0000

Data Index: 812093 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1003992 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1165476 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1390997 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0491. Min Act: -0.0000

Data Index: 1572583 (Python Code)

Max Activating Token Index: 410

Text #7

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0457. Min Act: -0.0000

Data Index: 63355 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0442. Min Act: -0.0000

Data Index: 767297 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0396. Min Act: -0.0000

Data Index: 1494312 (Python Code)

Max Activating Token Index: 370

Text #10

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0452. Min Act: -0.0000

Data Index: 209731 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0391. Min Act: -0.0000

Data Index: 1346824 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0419. Min Act: -0.0000

Data Index: 807050 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0410. Min Act: -0.0000

Data Index: 1596397 (Python Code)

Max Activating Token Index: 637

Text #14

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0407. Min Act: -0.0000

Data Index: 53902 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0405. Min Act: -0.0000

Data Index: 681681 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1033414 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0413. Min Act: -0.0000

Data Index: 928716 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0383. Min Act: -0.0000

Data Index: 227230 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0410. Min Act: -0.0000

Data Index: 1357341 (C4 (Web Text))

Max Activating Token Index: 799