Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 590 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.2006. Min Act: -0.0001

Data Index: 175043 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1779. Min Act: -0.0001

Data Index: 531536 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1882. Min Act: -0.0001

Data Index: 49386 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1804. Min Act: -0.0001

Data Index: 406744 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1312138 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1588. Min Act: -0.0001

Data Index: 736525 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1478. Min Act: -0.0001

Data Index: 406728 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1367. Min Act: -0.0001

Data Index: 743356 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1302956 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1280. Min Act: -0.0001

Data Index: 829134 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1300. Min Act: -0.0001

Data Index: 752446 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1380. Min Act: -0.0001

Data Index: 618562 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1181. Min Act: -0.0001

Data Index: 567936 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1288. Min Act: -0.0001

Data Index: 282465 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1049245 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1189. Min Act: -0.0001

Data Index: 936015 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1137400 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1261263 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1210. Min Act: -0.0001

Data Index: 910871 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1158. Min Act: -0.0001

Data Index: 293608 (C4 (Web Text))

Max Activating Token Index: 158