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

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

Neuron 633 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.1402. Min Act: 0.0000

Data Index: 92764 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.1745. Min Act: -0.0000

Data Index: 1250627 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.1141. Min Act: -0.0000

Data Index: 763286 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.1136. Min Act: -0.0000

Data Index: 403376 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.1265. Min Act: 0.0001

Data Index: 1019702 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.1085. Min Act: -0.0000

Data Index: 590109 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.0169. Min Act: 0.0000

Data Index: 1343878 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.0323. Min Act: -0.0000

Data Index: 327749 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1185206 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1276683 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9037. Min Act: -0.0000

Data Index: 775224 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9268. Min Act: 0.0000

Data Index: 1345391 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9040. Min Act: 0.0001

Data Index: 45857 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9039. Min Act: -0.0000

Data Index: 1215480 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8912. Min Act: -0.0000

Data Index: 202818 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1044718 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9033. Min Act: -0.0000

Data Index: 1317263 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8665. Min Act: -0.0000

Data Index: 525281 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8722. Min Act: -0.0000

Data Index: 116440 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8085. Min Act: -0.0000

Data Index: 468807 (C4 (Web Text))

Max Activating Token Index: 223