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

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

Neuron 1507 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: 0.1217. Min Range: -0.1217

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1011773 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1177521 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1347411 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1163. Min Act: -0.0002

Data Index: 1115840 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1076. Min Act: -0.0002

Data Index: 547830 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1032. Min Act: -0.0002

Data Index: 57817 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1278102 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1089. Min Act: -0.0002

Data Index: 466582 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0890. Min Act: -0.0001

Data Index: 707167 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1020. Min Act: -0.0002

Data Index: 426702 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1081. Min Act: -0.0002

Data Index: 185256 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1206. Min Act: -0.0002

Data Index: 645590 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1213522 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1216553 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1074. Min Act: -0.0002

Data Index: 15769 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1039. Min Act: -0.0002

Data Index: 647080 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1101. Min Act: -0.0001

Data Index: 1213131 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0966. Min Act: -0.0001

Data Index: 910548 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1047. Min Act: -0.0002

Data Index: 354786 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1059. Min Act: -0.0002

Data Index: 921302 (C4 (Web Text))

Max Activating Token Index: 658