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

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

Neuron 57 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1425616 (Python Code)

Max Activating Token Index: 76

Text #1

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1656530 (Python Code)

Max Activating Token Index: 274

Text #2

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1426254 (Python Code)

Max Activating Token Index: 120

Text #3

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1582047 (Python Code)

Max Activating Token Index: 111

Text #4

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1512953 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1544199 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1601391 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1521631 (Python Code)

Max Activating Token Index: 544

Text #8

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1611482 (Python Code)

Max Activating Token Index: 379

Text #9

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1454896 (Python Code)

Max Activating Token Index: 876

Text #10

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1557296 (Python Code)

Max Activating Token Index: 424

Text #11

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1394571 (Python Code)

Max Activating Token Index: 855

Text #12

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1443220 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1632013 (Python Code)

Max Activating Token Index: 404

Text #14

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1490179 (Python Code)

Max Activating Token Index: 265

Text #15

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1363111 (Python Code)

Max Activating Token Index: 709

Text #16

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1405447 (Python Code)

Max Activating Token Index: 948

Text #17

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1564967 (Python Code)

Max Activating Token Index: 127

Text #18

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1378731 (Python Code)

Max Activating Token Index: 452

Text #19

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1586739 (Python Code)

Max Activating Token Index: 65