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

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

Neuron 2508 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1569. Min Act: -0.0002

Data Index: 418096 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1227. Min Act: -0.0002

Data Index: 175174 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1833. Min Act: -0.0002

Data Index: 1337617 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0696. Min Act: -0.0002

Data Index: 868293 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0997. Min Act: -0.0002

Data Index: 839120 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.2225. Min Act: -0.0002

Data Index: 1168712 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1927. Min Act: -0.0002

Data Index: 451035 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1170. Min Act: -0.0002

Data Index: 498527 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1312. Min Act: -0.0002

Data Index: 960924 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.2966. Min Act: -0.0002

Data Index: 1251524 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 1.2966. Min Range: -1.2966

Max Act: 0.9578. Min Act: -0.0002

Data Index: 45751 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.2513. Min Act: -0.0002

Data Index: 370410 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0895. Min Act: -0.0002

Data Index: 1277112 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0491. Min Act: -0.0002

Data Index: 1349576 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1903. Min Act: -0.0002

Data Index: 1282100 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0996. Min Act: -0.0002

Data Index: 1011671 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1473. Min Act: -0.0002

Data Index: 940371 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1122. Min Act: -0.0002

Data Index: 263936 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 1.2966. Min Range: -1.2966

Max Act: 0.9271. Min Act: -0.0002

Data Index: 1334764 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.2966. Min Range: -1.2966

Max Act: 0.9446. Min Act: -0.0002

Data Index: 1083790 (C4 (Web Text))

Max Activating Token Index: 24