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

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

Neuron 4665 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1308714 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.6215. Min Act: -0.0000

Data Index: 933918 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5804. Min Act: -0.0000

Data Index: 811048 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5933. Min Act: -0.0000

Data Index: 459241 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5867. Min Act: -0.0000

Data Index: 866006 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1273797 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1164673 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5884. Min Act: -0.0000

Data Index: 687219 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5346. Min Act: -0.0000

Data Index: 525467 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5465. Min Act: -0.0000

Data Index: 200882 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1324406 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5234. Min Act: -0.0000

Data Index: 281667 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5494. Min Act: -0.0000

Data Index: 677932 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1329702 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5278. Min Act: -0.0000

Data Index: 80072 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5280. Min Act: -0.0000

Data Index: 988555 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4935. Min Act: -0.0000

Data Index: 189017 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1036950 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5225. Min Act: -0.0000

Data Index: 243163 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1131215 (C4 (Web Text))

Max Activating Token Index: 806