Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 274 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1019657 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1400644 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0191. Min Act: -0.0001

Data Index: 1120722 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1491709 (Python Code)

Max Activating Token Index: 982

Text #4

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0203. Min Act: -0.0001

Data Index: 825223 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0196. Min Act: -0.0001

Data Index: 545129 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1032309 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1596783 (Python Code)

Max Activating Token Index: 920

Text #8

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0204. Min Act: -0.0001

Data Index: 630166 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1614971 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0193. Min Act: -0.0001

Data Index: 1219338 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0187. Min Act: -0.0001

Data Index: 732617 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0192. Min Act: -0.0001

Data Index: 646975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1412410 (Python Code)

Max Activating Token Index: 938

Text #14

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0192. Min Act: -0.0001

Data Index: 890297 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0197. Min Act: -0.0001

Data Index: 4326 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0188. Min Act: -0.0001

Data Index: 16789 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1431908 (Python Code)

Max Activating Token Index: 986

Text #18

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0179. Min Act: -0.0001

Data Index: 461432 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0186. Min Act: -0.0001

Data Index: 931105 (C4 (Web Text))

Max Activating Token Index: 1023