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

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

Neuron 398 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1339. Min Range: -1.1339

Max Act: 1.1267. Min Act: -0.0001

Data Index: 1482655 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 1.1339. Min Range: -1.1339

Max Act: 1.1339. Min Act: -0.0001

Data Index: 1501620 (Python Code)

Max Activating Token Index: 112

Text #2

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.9760. Min Act: -0.0001

Data Index: 1427668 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8683. Min Act: -0.0001

Data Index: 1589982 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8023. Min Act: -0.0001

Data Index: 1569611 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8706. Min Act: -0.0001

Data Index: 1413263 (Python Code)

Max Activating Token Index: 978

Text #6

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8310. Min Act: -0.0001

Data Index: 1503787 (Python Code)

Max Activating Token Index: 416

Text #7

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8274. Min Act: -0.0001

Data Index: 1622660 (Python Code)

Max Activating Token Index: 834

Text #8

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1386407 (Python Code)

Max Activating Token Index: 275

Text #9

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8061. Min Act: -0.0001

Data Index: 1466345 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.7808. Min Act: -0.0001

Data Index: 1411051 (Python Code)

Max Activating Token Index: 275

Text #11

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.7811. Min Act: -0.0001

Data Index: 1411622 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1429670 (Python Code)

Max Activating Token Index: 656

Text #13

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1365446 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.7957. Min Act: -0.0001

Data Index: 1591009 (Python Code)

Max Activating Token Index: 257

Text #15

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1641725 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.7790. Min Act: -0.0001

Data Index: 1368670 (Python Code)

Max Activating Token Index: 640

Text #17

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.7800. Min Act: -0.0001

Data Index: 1627307 (Python Code)

Max Activating Token Index: 524

Text #18

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.7788. Min Act: -0.0001

Data Index: 1567028 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.7502. Min Act: -0.0001

Data Index: 1614269 (Python Code)

Max Activating Token Index: 931