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

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

Neuron 298 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: 0.1401. Min Range: -0.1401

Max Act: 0.1401. Min Act: -0.0003

Data Index: 1619324 (Python Code)

Max Activating Token Index: 262

Text #1

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1377. Min Act: -0.0003

Data Index: 1648376 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1268. Min Act: -0.0003

Data Index: 1456977 (Python Code)

Max Activating Token Index: 401

Text #3

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1377. Min Act: -0.0003

Data Index: 1585019 (Python Code)

Max Activating Token Index: 590

Text #4

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1265. Min Act: -0.0003

Data Index: 1510259 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1253. Min Act: -0.0003

Data Index: 1541082 (Python Code)

Max Activating Token Index: 268

Text #6

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1328. Min Act: -0.0003

Data Index: 1502152 (Python Code)

Max Activating Token Index: 321

Text #7

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1275. Min Act: -0.0003

Data Index: 1533908 (Python Code)

Max Activating Token Index: 414

Text #8

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1174. Min Act: -0.0003

Data Index: 1570004 (Python Code)

Max Activating Token Index: 887

Text #9

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1267. Min Act: -0.0003

Data Index: 1562088 (Python Code)

Max Activating Token Index: 461

Text #10

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1221. Min Act: -0.0003

Data Index: 1584110 (Python Code)

Max Activating Token Index: 245

Text #11

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1228. Min Act: -0.0003

Data Index: 1367856 (Python Code)

Max Activating Token Index: 228

Text #12

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1312. Min Act: -0.0003

Data Index: 1427460 (Python Code)

Max Activating Token Index: 229

Text #13

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1164. Min Act: -0.0003

Data Index: 1449179 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1160. Min Act: -0.0003

Data Index: 1495781 (Python Code)

Max Activating Token Index: 502

Text #15

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1208. Min Act: -0.0003

Data Index: 1523931 (Python Code)

Max Activating Token Index: 729

Text #16

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1237. Min Act: -0.0003

Data Index: 1604975 (Python Code)

Max Activating Token Index: 332

Text #17

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1106. Min Act: -0.0003

Data Index: 1571022 (Python Code)

Max Activating Token Index: 686

Text #18

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1095. Min Act: -0.0003

Data Index: 1370296 (Python Code)

Max Activating Token Index: 638

Text #19

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1180. Min Act: -0.0003

Data Index: 1451122 (Python Code)

Max Activating Token Index: 264