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

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

Neuron 834 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: 0.0268. Min Range: -0.0268

Max Act: 0.0268. Min Act: -0.0006

Data Index: 1223660 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0261. Min Act: -0.0006

Data Index: 682034 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0264. Min Act: -0.0006

Data Index: 800771 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0244. Min Act: -0.0006

Data Index: 342362 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1107843 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0239. Min Act: -0.0006

Data Index: 209053 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0235. Min Act: -0.0006

Data Index: 70928 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0239. Min Act: -0.0006

Data Index: 333792 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1205783 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0239. Min Act: -0.0006

Data Index: 156346 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1062770 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0227. Min Act: -0.0006

Data Index: 622581 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1098096 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0241. Min Act: -0.0006

Data Index: 1075301 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0235. Min Act: -0.0006

Data Index: 835844 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0230. Min Act: -0.0006

Data Index: 102537 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1179672 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0232. Min Act: -0.0006

Data Index: 346873 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0226. Min Act: -0.0006

Data Index: 403315 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0235. Min Act: -0.0006

Data Index: 40525 (C4 (Web Text))

Max Activating Token Index: 681