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

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

Neuron 3889 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0002

Data Index: 350849 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1038409 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1295. Min Act: -0.0002

Data Index: 1075297 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1424. Min Act: -0.0002

Data Index: 964588 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1218943 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1172. Min Act: -0.0002

Data Index: 831288 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1113332 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1156. Min Act: -0.0002

Data Index: 1320247 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1061. Min Act: -0.0002

Data Index: 332345 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1046. Min Act: -0.0001

Data Index: 849917 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1071. Min Act: -0.0002

Data Index: 126662 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1033. Min Act: -0.0001

Data Index: 386064 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1030. Min Act: -0.0002

Data Index: 926946 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0943. Min Act: -0.0001

Data Index: 272987 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0972. Min Act: -0.0001

Data Index: 998412 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1116338 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1048539 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1034. Min Act: -0.0002

Data Index: 679766 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0993. Min Act: -0.0001

Data Index: 815760 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0874. Min Act: -0.0002

Data Index: 222073 (C4 (Web Text))

Max Activating Token Index: 320