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

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

Neuron 3878 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1520035 (Python Code)

Max Activating Token Index: 489

Text #1

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0394. Min Act: -0.0000

Data Index: 1551698 (Python Code)

Max Activating Token Index: 1016

Text #2

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1482730 (Python Code)

Max Activating Token Index: 584

Text #3

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0379. Min Act: -0.0000

Data Index: 1102739 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0407. Min Act: -0.0000

Data Index: 1399713 (Python Code)

Max Activating Token Index: 502

Text #5

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0383. Min Act: -0.0000

Data Index: 1608280 (Python Code)

Max Activating Token Index: 922

Text #6

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0356. Min Act: -0.0000

Data Index: 890563 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0395. Min Act: 0.0001

Data Index: 1472498 (Python Code)

Max Activating Token Index: 662

Text #8

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1550750 (Python Code)

Max Activating Token Index: 640

Text #9

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1538297 (Python Code)

Max Activating Token Index: 751

Text #10

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0343. Min Act: -0.0000

Data Index: 1417523 (Python Code)

Max Activating Token Index: 571

Text #11

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1444690 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1404278 (Python Code)

Max Activating Token Index: 785

Text #13

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1363387 (Python Code)

Max Activating Token Index: 564

Text #14

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1236861 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0339. Min Act: -0.0000

Data Index: 566446 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1384714 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0353. Min Act: -0.0000

Data Index: 1542473 (Python Code)

Max Activating Token Index: 663

Text #18

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0342. Min Act: -0.0000

Data Index: 642520 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1429212 (Python Code)

Max Activating Token Index: 219