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

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

Neuron 1256 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1506. Min Act: -0.0002

Data Index: 747708 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1534. Min Act: -0.0002

Data Index: 463553 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1443. Min Act: -0.0002

Data Index: 1060950 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1414. Min Act: -0.0002

Data Index: 492090 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1263. Min Act: -0.0002

Data Index: 1210376 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1278. Min Act: -0.0002

Data Index: 998393 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1192. Min Act: -0.0002

Data Index: 745539 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1095941 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1245. Min Act: -0.0002

Data Index: 190487 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1193212 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1176. Min Act: -0.0002

Data Index: 202613 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1218. Min Act: -0.0002

Data Index: 967212 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1204. Min Act: -0.0002

Data Index: 226014 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1192. Min Act: -0.0002

Data Index: 599459 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1244. Min Act: -0.0002

Data Index: 1283019 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1195. Min Act: -0.0002

Data Index: 816826 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1151989 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1920 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1109. Min Act: -0.0002

Data Index: 76095 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1186. Min Act: -0.0002

Data Index: 200798 (C4 (Web Text))

Max Activating Token Index: 863