Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 452 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0209. Min Act: -0.0003

Data Index: 776786 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0200. Min Act: -0.0003

Data Index: 98807 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0190. Min Act: -0.0003

Data Index: 351853 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0194. Min Act: -0.0003

Data Index: 484999 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0179. Min Act: -0.0003

Data Index: 455328 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1326725 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0194. Min Act: -0.0003

Data Index: 655798 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0175. Min Act: -0.0003

Data Index: 807389 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0170. Min Act: -0.0003

Data Index: 31034 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0187. Min Act: -0.0003

Data Index: 1535677 (Python Code)

Max Activating Token Index: 786

Text #10

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1168687 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1315375 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1566477 (Python Code)

Max Activating Token Index: 814

Text #13

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0175. Min Act: -0.0003

Data Index: 939496 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0182. Min Act: -0.0003

Data Index: 101276 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1460225 (Python Code)

Max Activating Token Index: 917

Text #16

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1204526 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0178. Min Act: -0.0003

Data Index: 523573 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0177. Min Act: -0.0003

Data Index: 47106 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0168. Min Act: -0.0003

Data Index: 959958 (C4 (Web Text))

Max Activating Token Index: 552