Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1994 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0308. Min Act: -0.0002

Data Index: 268408 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0303. Min Act: -0.0002

Data Index: 391178 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0290. Min Act: -0.0002

Data Index: 700773 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0287. Min Act: -0.0002

Data Index: 161500 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0286. Min Act: -0.0002

Data Index: 539479 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0251. Min Act: -0.0002

Data Index: 252170 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0274. Min Act: -0.0002

Data Index: 567715 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0256. Min Act: -0.0002

Data Index: 467927 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0254. Min Act: -0.0002

Data Index: 876481 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0265. Min Act: -0.0002

Data Index: 152889 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1255853 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0251. Min Act: -0.0002

Data Index: 281541 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0258. Min Act: -0.0002

Data Index: 856888 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0254. Min Act: -0.0001

Data Index: 891125 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0247. Min Act: -0.0001

Data Index: 74627 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1048007 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1097540 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0248. Min Act: -0.0001

Data Index: 521844 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0239. Min Act: -0.0002

Data Index: 716178 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0252. Min Act: -0.0002

Data Index: 866682 (C4 (Web Text))

Max Activating Token Index: 213