Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1770 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0291. Min Act: -0.0006

Data Index: 716746 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0264. Min Act: -0.0006

Data Index: 781898 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0268. Min Act: -0.0006

Data Index: 1233585 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0292. Min Act: -0.0006

Data Index: 417241 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0255. Min Act: -0.0006

Data Index: 144952 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0255. Min Act: -0.0006

Data Index: 250237 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0252. Min Act: -0.0006

Data Index: 635352 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0241. Min Act: -0.0006

Data Index: 622050 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0247. Min Act: -0.0006

Data Index: 1012603 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1054529 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0243. Min Act: -0.0006

Data Index: 163820 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0248. Min Act: -0.0006

Data Index: 357276 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0241. Min Act: -0.0006

Data Index: 494898 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0241. Min Act: -0.0006

Data Index: 1200001 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0244. Min Act: -0.0006

Data Index: 896665 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1012705 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0227. Min Act: -0.0006

Data Index: 683587 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0232. Min Act: -0.0006

Data Index: 201775 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0242. Min Act: -0.0006

Data Index: 792979 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0237. Min Act: -0.0006

Data Index: 73773 (C4 (Web Text))

Max Activating Token Index: 831