Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1813 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2754. Min Act: -0.0002

Data Index: 601997 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2693. Min Act: -0.0002

Data Index: 1072829 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2537. Min Act: -0.0002

Data Index: 64281 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2281. Min Act: -0.0002

Data Index: 1276188 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2461. Min Act: -0.0002

Data Index: 856303 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2218. Min Act: -0.0002

Data Index: 1071216 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2335. Min Act: -0.0002

Data Index: 1235309 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2299. Min Act: -0.0002

Data Index: 830462 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2242. Min Act: -0.0002

Data Index: 1273696 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2384. Min Act: -0.0002

Data Index: 727944 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2255. Min Act: -0.0002

Data Index: 323055 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2125. Min Act: -0.0002

Data Index: 607557 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2087. Min Act: -0.0002

Data Index: 853428 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2014. Min Act: -0.0002

Data Index: 1072466 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2073. Min Act: -0.0002

Data Index: 423486 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2235. Min Act: -0.0002

Data Index: 1333683 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2219. Min Act: -0.0002

Data Index: 1120762 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2076. Min Act: -0.0002

Data Index: 1036714 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2273. Min Act: -0.0002

Data Index: 575981 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2190. Min Act: -0.0002

Data Index: 406338 (C4 (Web Text))

Max Activating Token Index: 184