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

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

Neuron 1788 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: 0.0213. Min Range: -0.0213

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1579273 (Python Code)

Max Activating Token Index: 1020

Text #1

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0203. Min Act: -0.0006

Data Index: 358483 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0207. Min Act: -0.0006

Data Index: 370897 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1327052 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0201. Min Act: -0.0006

Data Index: 789035 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1077094 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0204. Min Act: -0.0006

Data Index: 807772 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1130156 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1254551 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0199. Min Act: -0.0006

Data Index: 189809 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0193. Min Act: -0.0006

Data Index: 810774 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0198. Min Act: -0.0005

Data Index: 1005554 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1489514 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0193. Min Act: -0.0006

Data Index: 459333 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1205205 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0197. Min Act: -0.0006

Data Index: 516062 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1290851 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0192. Min Act: -0.0006

Data Index: 455664 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0191. Min Act: -0.0006

Data Index: 622754 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0195. Min Act: -0.0006

Data Index: 713787 (C4 (Web Text))

Max Activating Token Index: 785