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

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

Neuron 4164 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: 2.4283. Min Range: -2.4283

Max Act: 2.4283. Min Act: -0.0000

Data Index: 551655 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.9612. Min Act: -0.0000

Data Index: 1333755 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 2.4283. Min Range: -2.4283

Max Act: 2.0685. Min Act: -0.0000

Data Index: 890415 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.8778. Min Act: -0.0000

Data Index: 751512 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.8416. Min Act: -0.0000

Data Index: 418584 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.9189. Min Act: -0.0000

Data Index: 1077722 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.6722. Min Act: -0.0000

Data Index: 455670 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.6826. Min Act: -0.0000

Data Index: 987946 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.7441. Min Act: -0.0000

Data Index: 1312333 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.6315. Min Act: -0.0000

Data Index: 78568 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.5280. Min Act: -0.0000

Data Index: 553886 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.5911. Min Act: -0.0000

Data Index: 1271357 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.5742. Min Act: -0.0000

Data Index: 1251401 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.4627. Min Act: -0.0000

Data Index: 176099 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.5571. Min Act: -0.0000

Data Index: 1135082 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.4605. Min Act: -0.0000

Data Index: 588624 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.6196. Min Act: -0.0000

Data Index: 1065795 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.5367. Min Act: -0.0000

Data Index: 30987 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.5199. Min Act: -0.0000

Data Index: 150364 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.6024. Min Act: -0.0000

Data Index: 55391 (C4 (Web Text))

Max Activating Token Index: 129