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

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

Neuron 1281 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0001

Data Index: 478414 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0282. Min Act: -0.0001

Data Index: 107232 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0269. Min Act: -0.0001

Data Index: 646709 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0281. Min Act: -0.0001

Data Index: 968916 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0290. Min Act: -0.0001

Data Index: 13710 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1417434 (Python Code)

Max Activating Token Index: 524

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0266. Min Act: -0.0001

Data Index: 903596 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1352686 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1067940 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0250. Min Act: -0.0001

Data Index: 821099 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1442600 (Python Code)

Max Activating Token Index: 668

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0254. Min Act: -0.0001

Data Index: 112685 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1139595 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1561848 (Python Code)

Max Activating Token Index: 170

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0288. Min Act: -0.0001

Data Index: 434 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0255. Min Act: -0.0001

Data Index: 342276 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0233. Min Act: -0.0001

Data Index: 646718 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1144622 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0245. Min Act: -0.0001

Data Index: 282295 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0250. Min Act: -0.0001

Data Index: 1300449 (C4 (Web Text))

Max Activating Token Index: 464