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

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

Neuron 4345 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0268. Min Act: -0.0002

Data Index: 465954 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0257. Min Act: -0.0002

Data Index: 494037 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0273. Min Act: -0.0002

Data Index: 509785 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0258. Min Act: -0.0002

Data Index: 688656 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0258. Min Act: -0.0002

Data Index: 411957 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0254. Min Act: -0.0002

Data Index: 609346 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1271757 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1251606 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1027208 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0248. Min Act: -0.0002

Data Index: 132963 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0248. Min Act: -0.0002

Data Index: 793815 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0238. Min Act: -0.0002

Data Index: 712863 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1310742 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0227. Min Act: -0.0002

Data Index: 427320 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0226. Min Act: -0.0002

Data Index: 334120 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0235. Min Act: -0.0002

Data Index: 830650 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0228. Min Act: -0.0002

Data Index: 788915 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0226. Min Act: -0.0002

Data Index: 673555 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0216. Min Act: -0.0002

Data Index: 163185 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0223. Min Act: -0.0002

Data Index: 195957 (C4 (Web Text))

Max Activating Token Index: 405