Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 920 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1381. Min Act: -0.0002

Data Index: 180190 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1319. Min Act: -0.0002

Data Index: 753126 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1279. Min Act: -0.0002

Data Index: 1340571 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1178. Min Act: -0.0002

Data Index: 887704 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1038298 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1060. Min Act: 0.0001

Data Index: 583824 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1041. Min Act: 0.0001

Data Index: 388368 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0996. Min Act: -0.0003

Data Index: 267637 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1039. Min Act: -0.0002

Data Index: 43914 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1010. Min Act: -0.0003

Data Index: 1115961 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1051. Min Act: -0.0002

Data Index: 531765 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1053. Min Act: -0.0002

Data Index: 1321195 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1007. Min Act: -0.0003

Data Index: 411940 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1012. Min Act: -0.0003

Data Index: 20496 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1003. Min Act: -0.0003

Data Index: 901631 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1012. Min Act: -0.0003

Data Index: 349538 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0992. Min Act: -0.0002

Data Index: 819782 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0995. Min Act: -0.0002

Data Index: 216472 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0988. Min Act: -0.0003

Data Index: 683871 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0944. Min Act: -0.0003

Data Index: 238967 (C4 (Web Text))

Max Activating Token Index: 404