Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3659 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0273. Min Act: -0.0003

Data Index: 153339 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0003

Data Index: 138998 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1231214 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0233. Min Act: -0.0003

Data Index: 520816 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1311889 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1254264 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0242. Min Act: -0.0003

Data Index: 750524 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1276867 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1233883 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0250. Min Act: -0.0003

Data Index: 181707 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0230. Min Act: -0.0003

Data Index: 314555 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0201. Min Act: -0.0003

Data Index: 528496 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1355822 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0221. Min Act: -0.0003

Data Index: 175958 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0248. Min Act: -0.0003

Data Index: 26950 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1290343 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0230. Min Act: -0.0003

Data Index: 933429 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0211. Min Act: -0.0003

Data Index: 710468 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1204021 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1024144 (C4 (Web Text))

Max Activating Token Index: 483