Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 149 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0005

Data Index: 1153882 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0274. Min Act: -0.0005

Data Index: 46749 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0260. Min Act: -0.0005

Data Index: 1354366 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1501454 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0243. Min Act: -0.0005

Data Index: 1378851 (Python Code)

Max Activating Token Index: 407

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1505697 (Python Code)

Max Activating Token Index: 814

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0239. Min Act: -0.0005

Data Index: 1618126 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0236. Min Act: -0.0005

Data Index: 1644184 (Python Code)

Max Activating Token Index: 623

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0231. Min Act: -0.0005

Data Index: 1486702 (Python Code)

Max Activating Token Index: 544

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0229. Min Act: -0.0005

Data Index: 1386051 (Python Code)

Max Activating Token Index: 235

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0222. Min Act: -0.0005

Data Index: 1288051 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0231. Min Act: -0.0005

Data Index: 1653349 (Python Code)

Max Activating Token Index: 409

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0220. Min Act: -0.0005

Data Index: 1407402 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0224. Min Act: -0.0005

Data Index: 1611585 (Python Code)

Max Activating Token Index: 934

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0220. Min Act: -0.0005

Data Index: 1523562 (Python Code)

Max Activating Token Index: 659

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0216. Min Act: -0.0005

Data Index: 1543184 (Python Code)

Max Activating Token Index: 753

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0208. Min Act: -0.0005

Data Index: 1105977 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0217. Min Act: -0.0005

Data Index: 224546 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0205. Min Act: -0.0005

Data Index: 1366143 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0214. Min Act: -0.0005

Data Index: 1225097 (C4 (Web Text))

Max Activating Token Index: 212