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

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

Neuron 2233 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: 1.4234. Min Range: -1.4234

Max Act: 1.3692. Min Act: -0.0002

Data Index: 1595303 (Python Code)

Max Activating Token Index: 793

Text #1

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.3996. Min Act: -0.0002

Data Index: 1570720 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.3417. Min Act: -0.0002

Data Index: 1458384 (Python Code)

Max Activating Token Index: 850

Text #3

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.1844. Min Act: -0.0002

Data Index: 1475704 (Python Code)

Max Activating Token Index: 697

Text #4

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.2052. Min Act: -0.0002

Data Index: 1417686 (Python Code)

Max Activating Token Index: 288

Text #5

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.2770. Min Act: -0.0002

Data Index: 1452744 (Python Code)

Max Activating Token Index: 364

Text #6

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.3109. Min Act: -0.0002

Data Index: 1604328 (Python Code)

Max Activating Token Index: 628

Text #7

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.3561. Min Act: -0.0002

Data Index: 1626836 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.2621. Min Act: -0.0002

Data Index: 1539811 (Python Code)

Max Activating Token Index: 765

Text #9

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.2953. Min Act: -0.0002

Data Index: 1366019 (Python Code)

Max Activating Token Index: 367

Text #10

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.3113. Min Act: -0.0002

Data Index: 1442512 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.3810. Min Act: -0.0002

Data Index: 1532674 (Python Code)

Max Activating Token Index: 321

Text #12

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.2598. Min Act: -0.0002

Data Index: 1367660 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.1968. Min Act: -0.0002

Data Index: 1568594 (Python Code)

Max Activating Token Index: 581

Text #14

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.0795. Min Act: -0.0002

Data Index: 1501731 (Python Code)

Max Activating Token Index: 765

Text #15

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.2304. Min Act: -0.0002

Data Index: 1460253 (Python Code)

Max Activating Token Index: 651

Text #16

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.2716. Min Act: -0.0002

Data Index: 1613971 (Python Code)

Max Activating Token Index: 873

Text #17

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.4234. Min Act: -0.0002

Data Index: 1404663 (Python Code)

Max Activating Token Index: 752

Text #18

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.2567. Min Act: -0.0002

Data Index: 1580461 (Python Code)

Max Activating Token Index: 830

Text #19

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.2846. Min Act: -0.0002

Data Index: 1620782 (Python Code)

Max Activating Token Index: 671