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

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

Neuron 3730 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: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0002

Data Index: 1287939 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1532. Min Act: -0.0002

Data Index: 1271633 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1491. Min Act: -0.0002

Data Index: 985666 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1213. Min Act: -0.0002

Data Index: 78757 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1222. Min Act: -0.0002

Data Index: 734963 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1156. Min Act: -0.0002

Data Index: 1117540 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1244. Min Act: -0.0002

Data Index: 730128 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1141. Min Act: -0.0002

Data Index: 95327 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1049239 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1194474 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1014142 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1077. Min Act: -0.0002

Data Index: 1266927 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1076. Min Act: -0.0002

Data Index: 327842 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1031. Min Act: -0.0002

Data Index: 872783 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1028. Min Act: -0.0002

Data Index: 977003 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1080739 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1111. Min Act: -0.0002

Data Index: 49441 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1073. Min Act: -0.0002

Data Index: 179736 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0990. Min Act: -0.0002

Data Index: 617886 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1016397 (C4 (Web Text))

Max Activating Token Index: 917