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

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

Neuron 4237 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6853. Min Range: -6.6853

Max Act: 6.6853. Min Act: -0.0000

Data Index: 1495616 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 6.6853. Min Range: -6.6853

Max Act: 6.5371. Min Act: -0.0000

Data Index: 1456270 (Python Code)

Max Activating Token Index: 42

Text #2

Max Range: 6.6853. Min Range: -6.6853

Max Act: 5.9819. Min Act: -0.0000

Data Index: 1594803 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 6.6853. Min Range: -6.6853

Max Act: 5.8004. Min Act: -0.0000

Data Index: 1484171 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 6.6853. Min Range: -6.6853

Max Act: 5.2857. Min Act: -0.0000

Data Index: 1406427 (Python Code)

Max Activating Token Index: 99

Text #5

Max Range: 6.6853. Min Range: -6.6853

Max Act: 5.4232. Min Act: -0.0000

Data Index: 1543242 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 6.6853. Min Range: -6.6853

Max Act: 5.4394. Min Act: -0.0000

Data Index: 1492294 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 6.6853. Min Range: -6.6853

Max Act: 5.1438. Min Act: -0.0000

Data Index: 1654058 (Python Code)

Max Activating Token Index: 252

Text #8

Max Range: 6.6853. Min Range: -6.6853

Max Act: 5.0921. Min Act: -0.0000

Data Index: 1476893 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 6.6853. Min Range: -6.6853

Max Act: 5.2274. Min Act: -0.0000

Data Index: 1597513 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 6.6853. Min Range: -6.6853

Max Act: 5.1224. Min Act: -0.0000

Data Index: 1461892 (Python Code)

Max Activating Token Index: 215

Text #11

Max Range: 6.6853. Min Range: -6.6853

Max Act: 5.1230. Min Act: -0.0000

Data Index: 1402966 (Python Code)

Max Activating Token Index: 255

Text #12

Max Range: 6.6853. Min Range: -6.6853

Max Act: 4.9367. Min Act: -0.0000

Data Index: 1571845 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 6.6853. Min Range: -6.6853

Max Act: 4.9310. Min Act: -0.0000

Data Index: 1561430 (Python Code)

Max Activating Token Index: 121

Text #14

Max Range: 6.6853. Min Range: -6.6853

Max Act: 4.9098. Min Act: -0.0000

Data Index: 1475522 (Python Code)

Max Activating Token Index: 39

Text #15

Max Range: 6.6853. Min Range: -6.6853

Max Act: 4.7727. Min Act: -0.0000

Data Index: 1636721 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 6.6853. Min Range: -6.6853

Max Act: 4.9588. Min Act: -0.0000

Data Index: 1517458 (Python Code)

Max Activating Token Index: 284

Text #17

Max Range: 6.6853. Min Range: -6.6853

Max Act: 4.8703. Min Act: -0.0000

Data Index: 1582187 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 6.6853. Min Range: -6.6853

Max Act: 5.0239. Min Act: -0.0000

Data Index: 1426396 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 6.6853. Min Range: -6.6853

Max Act: 4.7132. Min Act: -0.0000

Data Index: 1375038 (Python Code)

Max Activating Token Index: 380