Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1777 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1392. Min Act: -0.0002

Data Index: 1324748 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1310. Min Act: -0.0002

Data Index: 760236 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1319. Min Act: -0.0002

Data Index: 1303123 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1204. Min Act: -0.0002

Data Index: 795772 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1008. Min Act: -0.0002

Data Index: 334116 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1236. Min Act: -0.0002

Data Index: 538173 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1146212 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1313491 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1135. Min Act: -0.0002

Data Index: 636869 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1049. Min Act: -0.0002

Data Index: 357177 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1073. Min Act: -0.0002

Data Index: 1212661 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1101. Min Act: -0.0002

Data Index: 671756 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1166. Min Act: -0.0002

Data Index: 126322 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1223368 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0992. Min Act: -0.0002

Data Index: 486135 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1035. Min Act: -0.0002

Data Index: 44015 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1137671 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0989. Min Act: -0.0002

Data Index: 69632 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1283687 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0997. Min Act: -0.0002

Data Index: 78009 (C4 (Web Text))

Max Activating Token Index: 363