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

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

Neuron 2086 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0000

Data Index: 1291232 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0228. Min Act: -0.0000

Data Index: 302427 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0238. Min Act: -0.0000

Data Index: 660965 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0234. Min Act: -0.0000

Data Index: 199260 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1506603 (Python Code)

Max Activating Token Index: 199

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0210. Min Act: -0.0000

Data Index: 31851 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0223. Min Act: -0.0000

Data Index: 1030905 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0233. Min Act: -0.0000

Data Index: 424680 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0245. Min Act: -0.0000

Data Index: 132557 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1386261 (Python Code)

Max Activating Token Index: 954

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0215. Min Act: -0.0000

Data Index: 47318 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0204. Min Act: -0.0000

Data Index: 752061 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0217. Min Act: -0.0000

Data Index: 433696 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0208. Min Act: -0.0000

Data Index: 719863 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0203. Min Act: -0.0000

Data Index: 1388490 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0206. Min Act: -0.0000

Data Index: 532842 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0201. Min Act: -0.0000

Data Index: 879920 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0202. Min Act: -0.0000

Data Index: 1190771 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0204. Min Act: -0.0000

Data Index: 253015 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0195. Min Act: -0.0000

Data Index: 1158944 (C4 (Web Text))

Max Activating Token Index: 704