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

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

Neuron 2524 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0308. Min Act: -0.0001

Data Index: 947212 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0288. Min Act: -0.0001

Data Index: 717979 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1585903 (Python Code)

Max Activating Token Index: 276

Text #3

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0254. Min Act: -0.0001

Data Index: 779070 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1625576 (Python Code)

Max Activating Token Index: 240

Text #5

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0258. Min Act: -0.0001

Data Index: 292220 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1242482 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0278. Min Act: -0.0001

Data Index: 593649 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1442523 (Python Code)

Max Activating Token Index: 411

Text #9

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1455336 (Python Code)

Max Activating Token Index: 854

Text #10

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0245. Min Act: -0.0001

Data Index: 275356 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1446923 (Python Code)

Max Activating Token Index: 146

Text #12

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0256. Min Act: -0.0001

Data Index: 878101 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1598901 (Python Code)

Max Activating Token Index: 737

Text #14

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0256. Min Act: -0.0001

Data Index: 1574446 (Python Code)

Max Activating Token Index: 1014

Text #15

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1400045 (Python Code)

Max Activating Token Index: 406

Text #16

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0245. Min Act: -0.0001

Data Index: 239141 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1611688 (Python Code)

Max Activating Token Index: 950

Text #18

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1198377 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0233. Min Act: -0.0001

Data Index: 1148448 (C4 (Web Text))

Max Activating Token Index: 238