Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4617 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1314. Min Act: -0.0002

Data Index: 1393895 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1311. Min Act: -0.0002

Data Index: 1469097 (Python Code)

Max Activating Token Index: 339

Text #2

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1483424 (Python Code)

Max Activating Token Index: 552

Text #3

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1177. Min Act: -0.0002

Data Index: 1511189 (Python Code)

Max Activating Token Index: 517

Text #4

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1252. Min Act: -0.0002

Data Index: 1591014 (Python Code)

Max Activating Token Index: 602

Text #5

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1165. Min Act: -0.0002

Data Index: 1611735 (Python Code)

Max Activating Token Index: 597

Text #6

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1196. Min Act: -0.0002

Data Index: 1499796 (Python Code)

Max Activating Token Index: 664

Text #7

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1439487 (Python Code)

Max Activating Token Index: 259

Text #8

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1165. Min Act: -0.0002

Data Index: 1503875 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1160. Min Act: -0.0002

Data Index: 1450236 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1194. Min Act: -0.0002

Data Index: 1631975 (Python Code)

Max Activating Token Index: 435

Text #11

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1165. Min Act: -0.0002

Data Index: 37780 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1551212 (Python Code)

Max Activating Token Index: 373

Text #13

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1117. Min Act: -0.0002

Data Index: 1548090 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1565541 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1500653 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1429288 (Python Code)

Max Activating Token Index: 717

Text #17

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1401988 (Python Code)

Max Activating Token Index: 702

Text #18

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1547628 (Python Code)

Max Activating Token Index: 116

Text #19

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1555769 (Python Code)

Max Activating Token Index: 388