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

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

Neuron 2668 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1744. Min Act: -0.0000

Data Index: 724094 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1469. Min Act: -0.0000

Data Index: 144935 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1441. Min Act: -0.0000

Data Index: 480108 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1406. Min Act: -0.0000

Data Index: 629774 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1385. Min Act: -0.0000

Data Index: 869809 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1341. Min Act: -0.0000

Data Index: 460591 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1281. Min Act: -0.0000

Data Index: 691900 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1282. Min Act: -0.0000

Data Index: 946070 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1127614 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1239. Min Act: -0.0000

Data Index: 1217057 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1382749 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1125. Min Act: -0.0000

Data Index: 969869 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1199. Min Act: -0.0000

Data Index: 231061 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1388. Min Act: -0.0000

Data Index: 667735 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1209. Min Act: -0.0000

Data Index: 442877 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1134899 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1429813 (Python Code)

Max Activating Token Index: 718

Text #17

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1186. Min Act: -0.0000

Data Index: 463771 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1189. Min Act: -0.0000

Data Index: 51423 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1325974 (C4 (Web Text))

Max Activating Token Index: 218