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

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

Neuron 3625 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.4211. Min Act: -0.0000

Data Index: 698181 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5901. Min Act: -0.0001

Data Index: 582207 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5609. Min Act: -0.0000

Data Index: 386663 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5522. Min Act: -0.0000

Data Index: 945310 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5350. Min Act: -0.0000

Data Index: 106179 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1083444 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5176. Min Act: -0.0000

Data Index: 489149 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5147. Min Act: -0.0000

Data Index: 296135 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1180101 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1039015 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5240. Min Act: -0.0000

Data Index: 365385 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.4771. Min Act: -0.0000

Data Index: 966977 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1677 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1152214 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1195143 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1348691 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.4833. Min Act: -0.0000

Data Index: 700336 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1130307 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.4671. Min Act: -0.0000

Data Index: 857370 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.5901. Min Range: -0.5901

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1023780 (C4 (Web Text))

Max Activating Token Index: 643