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

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

Neuron 941 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0389. Min Act: -0.0006

Data Index: 1021418 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0341. Min Act: -0.0006

Data Index: 1193413 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0334. Min Act: -0.0006

Data Index: 229670 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0322. Min Act: -0.0006

Data Index: 1083405 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0261. Min Act: -0.0006

Data Index: 306493 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1524155 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0225. Min Act: -0.0006

Data Index: 165573 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1577030 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1461199 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0230. Min Act: -0.0006

Data Index: 930005 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1495560 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1064036 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1418583 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0239. Min Act: -0.0006

Data Index: 895693 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0215. Min Act: -0.0005

Data Index: 863057 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0216. Min Act: -0.0006

Data Index: 748836 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0210. Min Act: -0.0006

Data Index: 418790 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1540779 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1483892 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0203. Min Act: -0.0006

Data Index: 867776 (C4 (Web Text))

Max Activating Token Index: 1023