Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1613 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.1148. Min Act: -0.0001

Data Index: 781322 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.1104. Min Act: -0.0001

Data Index: 478401 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0274. Min Act: -0.0000

Data Index: 949233 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0376. Min Act: -0.0001

Data Index: 597070 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0751. Min Act: -0.0001

Data Index: 878768 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0762. Min Act: -0.0001

Data Index: 905128 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.1279. Min Act: -0.0000

Data Index: 594470 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9334. Min Act: -0.0000

Data Index: 283127 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9256. Min Act: -0.0001

Data Index: 789071 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8667. Min Act: -0.0001

Data Index: 782871 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8400. Min Act: -0.0001

Data Index: 218899 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9009. Min Act: -0.0000

Data Index: 866654 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9354. Min Act: -0.0001

Data Index: 1164915 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8929. Min Act: -0.0001

Data Index: 625889 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8906. Min Act: -0.0001

Data Index: 182260 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9596. Min Act: -0.0001

Data Index: 565552 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1085466 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8201. Min Act: -0.0001

Data Index: 1065619 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.7222. Min Act: -0.0000

Data Index: 166323 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1351804 (C4 (Web Text))

Max Activating Token Index: 798