Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1000 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.9037. Min Act: -0.0000

Data Index: 1656064 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.4844. Min Act: -0.0000

Data Index: 1499932 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.4210. Min Act: -0.0000

Data Index: 1637022 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.4608. Min Act: -0.0000

Data Index: 1386156 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.5270. Min Act: -0.0000

Data Index: 1440922 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.4257. Min Act: -0.0000

Data Index: 1472730 (Python Code)

Max Activating Token Index: 505

Text #6

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.4077. Min Act: -0.0000

Data Index: 1409112 (Python Code)

Max Activating Token Index: 392

Text #7

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.3235. Min Act: -0.0000

Data Index: 1442673 (Python Code)

Max Activating Token Index: 936

Text #8

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.3504. Min Act: -0.0000

Data Index: 1471221 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.1635. Min Act: -0.0000

Data Index: 1478243 (Python Code)

Max Activating Token Index: 914

Text #10

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.3037. Min Act: -0.0000

Data Index: 1615783 (Python Code)

Max Activating Token Index: 1014

Text #11

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.1950. Min Act: -0.0000

Data Index: 1507631 (Python Code)

Max Activating Token Index: 504

Text #12

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.1234. Min Act: -0.0000

Data Index: 1640076 (Python Code)

Max Activating Token Index: 151

Text #13

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1087040 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.1635. Min Act: -0.0000

Data Index: 1411137 (Python Code)

Max Activating Token Index: 857

Text #15

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.1609. Min Act: -0.0000

Data Index: 1536602 (Python Code)

Max Activating Token Index: 530

Text #16

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.1431. Min Act: -0.0000

Data Index: 1144396 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.1342. Min Act: -0.0000

Data Index: 1390698 (Python Code)

Max Activating Token Index: 752

Text #18

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.1286. Min Act: -0.0000

Data Index: 1370169 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 1.9037. Min Range: -1.9037

Max Act: 1.1252. Min Act: -0.0000

Data Index: 1527173 (Python Code)

Max Activating Token Index: 657