Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1877 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1658. Min Act: -0.0003

Data Index: 350700 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1401. Min Act: -0.0003

Data Index: 135268 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1294. Min Act: -0.0003

Data Index: 1251244 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1394. Min Act: -0.0003

Data Index: 475714 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1309. Min Act: -0.0003

Data Index: 273843 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1340. Min Act: -0.0003

Data Index: 59779 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1226. Min Act: -0.0003

Data Index: 473885 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1021. Min Act: -0.0003

Data Index: 806218 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1232. Min Act: -0.0003

Data Index: 881965 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1200. Min Act: -0.0003

Data Index: 304677 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1147. Min Act: -0.0003

Data Index: 1016137 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1062. Min Act: -0.0003

Data Index: 80716 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1131. Min Act: -0.0003

Data Index: 1156855 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1212. Min Act: -0.0003

Data Index: 579186 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1043. Min Act: -0.0003

Data Index: 727179 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1125. Min Act: -0.0003

Data Index: 1221552 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1070. Min Act: -0.0003

Data Index: 1077565 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1139. Min Act: -0.0003

Data Index: 724781 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1180. Min Act: -0.0003

Data Index: 981137 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1090. Min Act: -0.0003

Data Index: 1269614 (C4 (Web Text))

Max Activating Token Index: 937