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

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

Neuron 2485 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.3852. Min Act: -0.0002

Data Index: 721515 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.4478. Min Act: -0.0002

Data Index: 938255 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.1849. Min Act: -0.0002

Data Index: 302705 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.1134. Min Act: -0.0002

Data Index: 351783 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.1430. Min Act: -0.0002

Data Index: 524441 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.1156. Min Act: -0.0002

Data Index: 259499 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.9278. Min Act: -0.0002

Data Index: 453862 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.9923. Min Act: -0.0002

Data Index: 1182321 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.0389. Min Act: -0.0002

Data Index: 239163 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.9871. Min Act: -0.0002

Data Index: 115944 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.9142. Min Act: -0.0002

Data Index: 341127 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.9530. Min Act: -0.0002

Data Index: 322252 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 1.4478. Min Range: -1.4478

Max Act: 1.0484. Min Act: -0.0002

Data Index: 710896 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.9834. Min Act: -0.0002

Data Index: 1225436 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.7918. Min Act: -0.0002

Data Index: 1165424 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.8199. Min Act: -0.0002

Data Index: 81819 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.9201. Min Act: -0.0002

Data Index: 247990 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.9298. Min Act: -0.0002

Data Index: 374156 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.9272. Min Act: -0.0002

Data Index: 1019228 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 1.4478. Min Range: -1.4478

Max Act: 0.8243. Min Act: -0.0002

Data Index: 270547 (C4 (Web Text))

Max Activating Token Index: 761