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

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

Neuron 581 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: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0005

Data Index: 791955 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1316409 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1219391 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0234. Min Act: -0.0006

Data Index: 742926 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0232. Min Act: -0.0006

Data Index: 434456 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1178918 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0234. Min Act: -0.0005

Data Index: 1011423 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0231. Min Act: -0.0005

Data Index: 1090180 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0231. Min Act: -0.0005

Data Index: 785159 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0234. Min Act: -0.0006

Data Index: 734022 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0221. Min Act: -0.0006

Data Index: 784566 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0226. Min Act: -0.0005

Data Index: 1305130 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0220. Min Act: -0.0006

Data Index: 883842 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0224. Min Act: -0.0005

Data Index: 548848 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0213. Min Act: -0.0006

Data Index: 45290 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0218. Min Act: -0.0006

Data Index: 913465 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0220. Min Act: -0.0006

Data Index: 859050 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0210. Min Act: -0.0006

Data Index: 674661 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0215. Min Act: -0.0005

Data Index: 541032 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0219. Min Act: -0.0006

Data Index: 298276 (C4 (Web Text))

Max Activating Token Index: 1009