Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4074 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1567678 (Python Code)

Max Activating Token Index: 951

Text #1

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1372. Min Act: -0.0001

Data Index: 1575023 (Python Code)

Max Activating Token Index: 154

Text #2

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1484616 (Python Code)

Max Activating Token Index: 216

Text #3

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1633233 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1592013 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1384339 (Python Code)

Max Activating Token Index: 911

Text #6

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1409269 (Python Code)

Max Activating Token Index: 395

Text #7

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1445416 (Python Code)

Max Activating Token Index: 403

Text #8

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1575198 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1509457 (Python Code)

Max Activating Token Index: 351

Text #10

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1540159 (Python Code)

Max Activating Token Index: 551

Text #11

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1624641 (Python Code)

Max Activating Token Index: 101

Text #12

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1430994 (Python Code)

Max Activating Token Index: 729

Text #13

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1438896 (Python Code)

Max Activating Token Index: 372

Text #14

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1428568 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1426614 (Python Code)

Max Activating Token Index: 786

Text #16

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1641418 (Python Code)

Max Activating Token Index: 147

Text #17

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1646450 (Python Code)

Max Activating Token Index: 932

Text #18

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1481031 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1614440 (Python Code)

Max Activating Token Index: 42