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

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

Neuron 4158 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0338. Min Act: -0.0002

Data Index: 572487 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0350. Min Act: -0.0002

Data Index: 774891 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1356621 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0276. Min Act: -0.0002

Data Index: 78913 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0274. Min Act: -0.0002

Data Index: 920924 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0317. Min Act: -0.0002

Data Index: 887993 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0311. Min Act: -0.0002

Data Index: 264276 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1610362 (Python Code)

Max Activating Token Index: 212

Text #8

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1181611 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0241. Min Act: -0.0002

Data Index: 41722 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0255. Min Act: -0.0002

Data Index: 957136 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1203186 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0213. Min Act: -0.0002

Data Index: 933106 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0275. Min Act: -0.0002

Data Index: 349320 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0265. Min Act: -0.0003

Data Index: 251361 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0180. Min Act: -0.0002

Data Index: 583335 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0286. Min Act: -0.0002

Data Index: 933429 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0254. Min Act: -0.0002

Data Index: 199820 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1471255 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0261. Min Act: -0.0002

Data Index: 957864 (C4 (Web Text))

Max Activating Token Index: 451