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

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

Neuron 1822 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: 0.0245. Min Range: -0.0245

Max Act: 0.0241. Min Act: -0.0005

Data Index: 794679 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0245. Min Act: -0.0005

Data Index: 469199 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0208. Min Act: -0.0005

Data Index: 102123 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0212. Min Act: -0.0006

Data Index: 811802 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0202. Min Act: -0.0005

Data Index: 1156799 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0197. Min Act: -0.0005

Data Index: 869827 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0198. Min Act: -0.0006

Data Index: 747386 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0196. Min Act: -0.0006

Data Index: 594962 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0199. Min Act: -0.0005

Data Index: 325989 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0190. Min Act: -0.0006

Data Index: 970333 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0194. Min Act: -0.0005

Data Index: 1125300 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1092637 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0190. Min Act: -0.0006

Data Index: 344505 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0189. Min Act: -0.0006

Data Index: 958515 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0174. Min Act: -0.0005

Data Index: 1156912 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1071524 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1211919 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0186. Min Act: -0.0005

Data Index: 573103 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0182. Min Act: -0.0005

Data Index: 123595 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1137500 (C4 (Web Text))

Max Activating Token Index: 80