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

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

Neuron 3838 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1417565 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0415. Min Act: -0.0000

Data Index: 1551461 (Python Code)

Max Activating Token Index: 857

Text #2

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1418608 (Python Code)

Max Activating Token Index: 772

Text #3

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1541509 (Python Code)

Max Activating Token Index: 466

Text #4

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0306. Min Act: -0.0000

Data Index: 453367 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1610915 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0299. Min Act: -0.0000

Data Index: 1413035 (Python Code)

Max Activating Token Index: 370

Text #7

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1523046 (Python Code)

Max Activating Token Index: 714

Text #8

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0265. Min Act: -0.0000

Data Index: 1457871 (Python Code)

Max Activating Token Index: 412

Text #9

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0243. Min Act: -0.0000

Data Index: 808341 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0266. Min Act: -0.0000

Data Index: 1515945 (Python Code)

Max Activating Token Index: 799

Text #11

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0256. Min Act: -0.0000

Data Index: 1462981 (Python Code)

Max Activating Token Index: 820

Text #12

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0245. Min Act: -0.0000

Data Index: 1481501 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0241. Min Act: -0.0000

Data Index: 1540519 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0266. Min Act: -0.0000

Data Index: 1547060 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0241. Min Act: -0.0000

Data Index: 1651670 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0195. Min Act: -0.0000

Data Index: 112935 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1500753 (Python Code)

Max Activating Token Index: 453

Text #18

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0245. Min Act: -0.0000

Data Index: 1587021 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0169. Min Act: -0.0000

Data Index: 1478598 (Python Code)

Max Activating Token Index: 126