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

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

Neuron 1574 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1246193 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1079030 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0220. Min Act: -0.0006

Data Index: 1568031 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0213. Min Act: -0.0005

Data Index: 445042 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0207. Min Act: -0.0006

Data Index: 251093 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0204. Min Act: -0.0006

Data Index: 431058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1650358 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0208. Min Act: -0.0005

Data Index: 1300692 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0208. Min Act: -0.0005

Data Index: 1372647 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0200. Min Act: -0.0006

Data Index: 35466 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0199. Min Act: -0.0006

Data Index: 305469 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0203. Min Act: -0.0006

Data Index: 251494 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0203. Min Act: -0.0006

Data Index: 575815 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0202. Min Act: -0.0005

Data Index: 506307 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0201. Min Act: -0.0006

Data Index: 974063 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0199. Min Act: -0.0005

Data Index: 253348 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0194. Min Act: -0.0006

Data Index: 268374 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0198. Min Act: -0.0005

Data Index: 1040326 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1656061 (Python Code)

Max Activating Token Index: 674

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0197. Min Act: -0.0006

Data Index: 42868 (C4 (Web Text))

Max Activating Token Index: 1023