Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3457 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1527965 (Python Code)

Max Activating Token Index: 676

Text #1

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0221. Min Act: -0.0002

Data Index: 435618 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0226. Min Act: -0.0002

Data Index: 254796 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0213. Min Act: -0.0002

Data Index: 506418 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0208. Min Act: -0.0001

Data Index: 768339 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1289827 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0208. Min Act: -0.0002

Data Index: 996734 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0209. Min Act: -0.0002

Data Index: 323302 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0214. Min Act: -0.0002

Data Index: 654674 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1231920 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0212. Min Act: -0.0002

Data Index: 190190 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1228126 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0193. Min Act: -0.0002

Data Index: 229661 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0204. Min Act: -0.0002

Data Index: 179703 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0198. Min Act: -0.0002

Data Index: 10090 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0214. Min Act: -0.0002

Data Index: 134514 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0205. Min Act: -0.0002

Data Index: 361372 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0209. Min Act: -0.0001

Data Index: 965699 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0218. Min Act: -0.0002

Data Index: 833083 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0186. Min Act: -0.0001

Data Index: 1523111 (Python Code)

Max Activating Token Index: 794