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

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

Neuron 1653 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0347. Min Act: -0.0004

Data Index: 756796 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1225128 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0275. Min Act: -0.0002

Data Index: 883552 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0275. Min Act: -0.0003

Data Index: 672703 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0272. Min Act: -0.0003

Data Index: 952208 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0247. Min Act: -0.0003

Data Index: 162107 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0274. Min Act: -0.0003

Data Index: 732955 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0266. Min Act: -0.0002

Data Index: 550546 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0263. Min Act: -0.0002

Data Index: 919984 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1419265 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0265. Min Act: -0.0003

Data Index: 957854 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0235. Min Act: -0.0003

Data Index: 713667 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0243. Min Act: -0.0003

Data Index: 440757 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0262. Min Act: -0.0004

Data Index: 147692 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0263. Min Act: -0.0003

Data Index: 378895 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0252. Min Act: -0.0003

Data Index: 740815 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0250. Min Act: -0.0003

Data Index: 626380 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0248. Min Act: -0.0002

Data Index: 869456 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0251. Min Act: -0.0004

Data Index: 851860 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0249. Min Act: -0.0003

Data Index: 467866 (C4 (Web Text))

Max Activating Token Index: 106