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

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

Neuron 5170 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: 0.1793. Min Range: -0.1793

Max Act: 0.1793. Min Act: -0.0002

Data Index: 213498 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1699. Min Act: -0.0002

Data Index: 551099 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1768. Min Act: -0.0002

Data Index: 1309184 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1644. Min Act: -0.0002

Data Index: 533592 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1653. Min Act: -0.0002

Data Index: 600464 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1595. Min Act: -0.0002

Data Index: 531556 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1322. Min Act: -0.0002

Data Index: 202483 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1282. Min Act: -0.0002

Data Index: 36903 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1139. Min Act: -0.0002

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1226309 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1163. Min Act: -0.0002

Data Index: 750693 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1144. Min Act: -0.0002

Data Index: 920120 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1055657 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1082. Min Act: -0.0002

Data Index: 280151 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1074. Min Act: -0.0002

Data Index: 519506 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1098. Min Act: -0.0002

Data Index: 304355 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1075. Min Act: -0.0002

Data Index: 58855 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1340704 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1066. Min Act: -0.0002

Data Index: 822960 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1031. Min Act: -0.0002

Data Index: 565869 (C4 (Web Text))

Max Activating Token Index: 613