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

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

Neuron 3325 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: 3.6412. Min Range: -3.6412

Max Act: 3.6412. Min Act: -0.0000

Data Index: 1387700 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.8215. Min Act: -0.0000

Data Index: 1545439 (Python Code)

Max Activating Token Index: 1010

Text #2

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.8319. Min Act: -0.0000

Data Index: 1365260 (Python Code)

Max Activating Token Index: 391

Text #3

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.7782. Min Act: -0.0000

Data Index: 1539743 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.4724. Min Act: -0.0000

Data Index: 1633690 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.4062. Min Act: -0.0000

Data Index: 1507012 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.5085. Min Act: -0.0000

Data Index: 1614059 (Python Code)

Max Activating Token Index: 162

Text #7

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.4879. Min Act: -0.0000

Data Index: 1405809 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.4669. Min Act: -0.0000

Data Index: 1558511 (Python Code)

Max Activating Token Index: 614

Text #9

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.2631. Min Act: -0.0000

Data Index: 1484853 (Python Code)

Max Activating Token Index: 438

Text #10

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.4400. Min Act: -0.0000

Data Index: 1368659 (Python Code)

Max Activating Token Index: 230

Text #11

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.1399. Min Act: -0.0000

Data Index: 1489249 (Python Code)

Max Activating Token Index: 811

Text #12

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.3726. Min Act: -0.0000

Data Index: 1362294 (Python Code)

Max Activating Token Index: 475

Text #13

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.4390. Min Act: -0.0000

Data Index: 1524834 (Python Code)

Max Activating Token Index: 542

Text #14

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.3645. Min Act: -0.0000

Data Index: 1588125 (Python Code)

Max Activating Token Index: 789

Text #15

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.1182. Min Act: -0.0000

Data Index: 1584816 (Python Code)

Max Activating Token Index: 249

Text #16

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.4603. Min Act: -0.0000

Data Index: 1380448 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.2172. Min Act: -0.0000

Data Index: 1459323 (Python Code)

Max Activating Token Index: 939

Text #18

Max Range: 3.6412. Min Range: -3.6412

Max Act: 2.1173. Min Act: -0.0000

Data Index: 1452553 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 3.6412. Min Range: -3.6412

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1410751 (Python Code)

Max Activating Token Index: 647