Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3100 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1149 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0280. Min Act: -0.0001

Data Index: 886546 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1570537 (Python Code)

Max Activating Token Index: 508

Text #3

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0260. Min Act: -0.0001

Data Index: 385194 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1506525 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1449005 (Python Code)

Max Activating Token Index: 809

Text #6

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1431723 (Python Code)

Max Activating Token Index: 933

Text #7

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0230. Min Act: -0.0001

Data Index: 181002 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1108388 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1233798 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0239. Min Act: -0.0001

Data Index: 299325 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0250. Min Act: -0.0001

Data Index: 1617280 (Python Code)

Max Activating Token Index: 567

Text #12

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1495813 (Python Code)

Max Activating Token Index: 930

Text #13

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1406666 (Python Code)

Max Activating Token Index: 612

Text #14

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0229. Min Act: -0.0001

Data Index: 1562152 (Python Code)

Max Activating Token Index: 586

Text #15

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1435000 (Python Code)

Max Activating Token Index: 813

Text #16

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0235. Min Act: -0.0002

Data Index: 327436 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1157716 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1524500 (Python Code)

Max Activating Token Index: 488

Text #19

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1506899 (Python Code)

Max Activating Token Index: 715