Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1144 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1591630 (Python Code)

Max Activating Token Index: 266

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0278. Min Act: -0.0000

Data Index: 1291446 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0246. Min Act: -0.0000

Data Index: 93993 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0233. Min Act: -0.0000

Data Index: 158832 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0220. Min Act: -0.0000

Data Index: 389377 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0233. Min Act: -0.0000

Data Index: 1231807 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0212. Min Act: -0.0000

Data Index: 918608 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0206. Min Act: -0.0000

Data Index: 942917 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0211. Min Act: -0.0000

Data Index: 892397 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0199. Min Act: -0.0000

Data Index: 304770 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0204. Min Act: -0.0000

Data Index: 962436 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0209. Min Act: -0.0000

Data Index: 231964 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0201. Min Act: -0.0000

Data Index: 686006 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0212. Min Act: -0.0000

Data Index: 582669 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0202. Min Act: -0.0000

Data Index: 943987 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0196. Min Act: -0.0000

Data Index: 123673 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0189. Min Act: -0.0000

Data Index: 787105 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0188. Min Act: -0.0000

Data Index: 188609 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0201. Min Act: -0.0000

Data Index: 646740 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0189. Min Act: -0.0000

Data Index: 614343 (C4 (Web Text))

Max Activating Token Index: 189