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

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

Neuron 4344 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1512474 (Python Code)

Max Activating Token Index: 922

Text #1

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1571947 (Python Code)

Max Activating Token Index: 747

Text #2

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1460309 (Python Code)

Max Activating Token Index: 293

Text #3

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1366164 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1508514 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1643085 (Python Code)

Max Activating Token Index: 662

Text #6

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1410039 (Python Code)

Max Activating Token Index: 1007

Text #7

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1159. Min Act: -0.0001

Data Index: 221794 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1185. Min Act: -0.0001

Data Index: 444327 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1229. Min Act: -0.0001

Data Index: 856725 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1169. Min Act: -0.0000

Data Index: 948913 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1624718 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1136. Min Act: -0.0000

Data Index: 146606 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1106. Min Act: -0.0000

Data Index: 993613 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1085. Min Act: -0.0001

Data Index: 183637 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1388101 (Python Code)

Max Activating Token Index: 218

Text #16

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1330870 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1212. Min Act: -0.0000

Data Index: 624130 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1544541 (Python Code)

Max Activating Token Index: 44

Text #19

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1179. Min Act: -0.0001

Data Index: 17515 (C4 (Web Text))

Max Activating Token Index: 190