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

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

Neuron 1438 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: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1469281 (Python Code)

Max Activating Token Index: 402

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0239. Min Act: -0.0006

Data Index: 113826 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0226. Min Act: -0.0006

Data Index: 353938 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0219. Min Act: -0.0006

Data Index: 368199 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0218. Min Act: -0.0006

Data Index: 584840 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1331770 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0212. Min Act: -0.0006

Data Index: 363781 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1081936 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0214. Min Act: -0.0005

Data Index: 1058355 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0205. Min Act: -0.0006

Data Index: 130019 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0213. Min Act: -0.0006

Data Index: 374516 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0204. Min Act: -0.0006

Data Index: 116453 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0219. Min Act: -0.0006

Data Index: 462345 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1254341 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0196. Min Act: -0.0006

Data Index: 231067 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0193. Min Act: -0.0006

Data Index: 172842 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1289520 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0200. Min Act: -0.0006

Data Index: 869745 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0197. Min Act: -0.0006

Data Index: 377879 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1102482 (C4 (Web Text))

Max Activating Token Index: 292