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

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

Neuron 2029 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.5833. Min Act: -0.0001

Data Index: 1022175 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.5797. Min Act: -0.0001

Data Index: 1079510 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.4339. Min Act: -0.0001

Data Index: 71389 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.4213. Min Act: -0.0001

Data Index: 323330 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.3324. Min Act: -0.0001

Data Index: 106865 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.3004. Min Act: -0.0001

Data Index: 967823 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.2407. Min Act: -0.0001

Data Index: 1123275 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.1129. Min Act: -0.0001

Data Index: 1148130 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.1166. Min Act: -0.0001

Data Index: 904123 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.0598. Min Act: -0.0001

Data Index: 1249338 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.0119. Min Act: -0.0001

Data Index: 695766 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.5833. Min Range: -1.5833

Max Act: 0.9776. Min Act: -0.0001

Data Index: 948663 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.5833. Min Range: -1.5833

Max Act: 0.9645. Min Act: -0.0001

Data Index: 1049293 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.0039. Min Act: -0.0001

Data Index: 31032 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.0019. Min Act: -0.0001

Data Index: 223235 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 1.5833. Min Range: -1.5833

Max Act: 0.9488. Min Act: -0.0001

Data Index: 1292142 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.5833. Min Range: -1.5833

Max Act: 1.0645. Min Act: -0.0000

Data Index: 618007 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.5833. Min Range: -1.5833

Max Act: 0.9765. Min Act: -0.0001

Data Index: 677368 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 1.5833. Min Range: -1.5833

Max Act: 0.9689. Min Act: -0.0001

Data Index: 711543 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 1.5833. Min Range: -1.5833

Max Act: 0.8753. Min Act: -0.0001

Data Index: 30578 (C4 (Web Text))

Max Activating Token Index: 683