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

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

Neuron 5446 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: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0001

Data Index: 884668 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1084475 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1337. Min Act: -0.0001

Data Index: 352304 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1239. Min Act: -0.0001

Data Index: 332601 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1304. Min Act: -0.0001

Data Index: 1240866 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1381. Min Act: -0.0001

Data Index: 3162 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1315. Min Act: -0.0001

Data Index: 673244 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1254. Min Act: -0.0001

Data Index: 252513 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1234. Min Act: -0.0001

Data Index: 556762 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1193. Min Act: -0.0001

Data Index: 766555 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1108032 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1146. Min Act: -0.0001

Data Index: 585768 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1195663 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1040819 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1195. Min Act: -0.0001

Data Index: 458519 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1180. Min Act: -0.0002

Data Index: 704010 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1088. Min Act: -0.0002

Data Index: 661101 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1196. Min Act: -0.0001

Data Index: 919698 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1241181 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1000329 (C4 (Web Text))

Max Activating Token Index: 29