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

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

Neuron 1658 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: 0.0255. Min Range: -0.0255

Max Act: 0.0255. Min Act: -0.0006

Data Index: 75098 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0239. Min Act: -0.0006

Data Index: 901523 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0219. Min Act: -0.0006

Data Index: 342228 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0215. Min Act: -0.0006

Data Index: 311419 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1031545 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1455534 (Python Code)

Max Activating Token Index: 272

Text #6

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1484456 (Python Code)

Max Activating Token Index: 201

Text #7

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1597743 (Python Code)

Max Activating Token Index: 255

Text #8

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1433186 (Python Code)

Max Activating Token Index: 791

Text #9

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1432045 (Python Code)

Max Activating Token Index: 790

Text #10

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0201. Min Act: -0.0006

Data Index: 549272 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1409155 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1406268 (Python Code)

Max Activating Token Index: 198

Text #13

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1462122 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1438340 (Python Code)

Max Activating Token Index: 823

Text #15

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1433293 (Python Code)

Max Activating Token Index: 264

Text #16

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0190. Min Act: -0.0006

Data Index: 465871 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1542807 (Python Code)

Max Activating Token Index: 265

Text #18

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1451592 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1370375 (Python Code)

Max Activating Token Index: 238