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

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

Neuron 4879 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: 1.3720. Min Range: -1.3720

Max Act: 1.3165. Min Act: -0.0000

Data Index: 1575481 (Python Code)

Max Activating Token Index: 231

Text #1

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1592536 (Python Code)

Max Activating Token Index: 607

Text #2

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.3720. Min Act: -0.0000

Data Index: 1465515 (Python Code)

Max Activating Token Index: 588

Text #3

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2934. Min Act: -0.0000

Data Index: 1441738 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1491928 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1647346 (Python Code)

Max Activating Token Index: 326

Text #6

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2672. Min Act: -0.0000

Data Index: 1374599 (Python Code)

Max Activating Token Index: 44

Text #7

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1605881 (Python Code)

Max Activating Token Index: 993

Text #8

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1651659 (Python Code)

Max Activating Token Index: 219

Text #9

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1562657 (Python Code)

Max Activating Token Index: 169

Text #10

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1534089 (Python Code)

Max Activating Token Index: 912

Text #11

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1513337 (Python Code)

Max Activating Token Index: 706

Text #12

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2242. Min Act: -0.0000

Data Index: 1568355 (Python Code)

Max Activating Token Index: 719

Text #13

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1513429 (Python Code)

Max Activating Token Index: 101

Text #14

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1455878 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1642. Min Act: -0.0000

Data Index: 1367377 (Python Code)

Max Activating Token Index: 652

Text #16

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1504693 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2374. Min Act: -0.0000

Data Index: 1392652 (Python Code)

Max Activating Token Index: 450

Text #18

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1655755 (Python Code)

Max Activating Token Index: 174

Text #19

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1543465 (Python Code)

Max Activating Token Index: 153