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

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

Neuron 3331 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0262. Min Act: -0.0001

Data Index: 340213 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0232. Min Act: -0.0001

Data Index: 130142 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0231. Min Act: -0.0001

Data Index: 875551 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0227. Min Act: -0.0001

Data Index: 446619 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0227. Min Act: -0.0001

Data Index: 137872 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0223. Min Act: -0.0001

Data Index: 771744 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0223. Min Act: -0.0001

Data Index: 333186 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0213. Min Act: -0.0001

Data Index: 655274 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0213. Min Act: -0.0001

Data Index: 768103 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0215. Min Act: -0.0001

Data Index: 645405 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0209. Min Act: -0.0001

Data Index: 164013 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0208. Min Act: -0.0001

Data Index: 662196 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0208. Min Act: -0.0001

Data Index: 552633 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1168534 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0202. Min Act: -0.0001

Data Index: 1592882 (Python Code)

Max Activating Token Index: 918

Text #15

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0205. Min Act: -0.0001

Data Index: 288408 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0199. Min Act: -0.0001

Data Index: 63825 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0200. Min Act: -0.0001

Data Index: 21833 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0196. Min Act: -0.0001

Data Index: 115494 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0199. Min Act: -0.0001

Data Index: 768871 (C4 (Web Text))

Max Activating Token Index: 479