Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 110 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0424. Min Act: -0.0006

Data Index: 939541 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0357. Min Act: -0.0006

Data Index: 1371295 (Python Code)

Max Activating Token Index: 288

Text #2

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0286. Min Act: -0.0006

Data Index: 293844 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1561825 (Python Code)

Max Activating Token Index: 221

Text #4

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0258. Min Act: -0.0006

Data Index: 1441512 (Python Code)

Max Activating Token Index: 653

Text #5

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0242. Min Act: -0.0006

Data Index: 747194 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0242. Min Act: -0.0006

Data Index: 831332 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0247. Min Act: -0.0006

Data Index: 1484310 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0232. Min Act: -0.0006

Data Index: 896081 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0201. Min Act: -0.0006

Data Index: 434152 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0227. Min Act: -0.0006

Data Index: 664266 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1423213 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0213. Min Act: -0.0006

Data Index: 260392 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0216. Min Act: -0.0006

Data Index: 1457909 (Python Code)

Max Activating Token Index: 77

Text #14

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1419189 (Python Code)

Max Activating Token Index: 268

Text #15

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1305699 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0198. Min Act: -0.0006

Data Index: 447292 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1472339 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0209. Min Act: -0.0006

Data Index: 195159 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1461430 (Python Code)

Max Activating Token Index: 47