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

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

Neuron 1250 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: 1.8229. Min Range: -1.8229

Max Act: 1.8229. Min Act: -0.0001

Data Index: 1543783 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.4747. Min Act: -0.0000

Data Index: 1518129 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.4747. Min Act: -0.0000

Data Index: 1588276 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2254. Min Act: -0.0000

Data Index: 1469855 (Python Code)

Max Activating Token Index: 742

Text #4

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.5156. Min Act: -0.0001

Data Index: 1635034 (Python Code)

Max Activating Token Index: 33

Text #5

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.4269. Min Act: -0.0001

Data Index: 1531929 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.3316. Min Act: -0.0000

Data Index: 1495225 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.3949. Min Act: -0.0001

Data Index: 1381246 (Python Code)

Max Activating Token Index: 240

Text #8

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.3189. Min Act: -0.0001

Data Index: 1629549 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.3548. Min Act: -0.0001

Data Index: 1616294 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.3102. Min Act: -0.0001

Data Index: 1473863 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.4614. Min Act: -0.0001

Data Index: 1373785 (Python Code)

Max Activating Token Index: 783

Text #12

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2635. Min Act: -0.0000

Data Index: 1599924 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2934. Min Act: -0.0001

Data Index: 1485369 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1483131 (Python Code)

Max Activating Token Index: 187

Text #15

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2282. Min Act: -0.0001

Data Index: 1411420 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2880. Min Act: -0.0001

Data Index: 1526770 (Python Code)

Max Activating Token Index: 449

Text #17

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2838. Min Act: -0.0001

Data Index: 1411573 (Python Code)

Max Activating Token Index: 44

Text #18

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.1556. Min Act: -0.0001

Data Index: 1435335 (Python Code)

Max Activating Token Index: 56

Text #19

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2203. Min Act: -0.0000

Data Index: 1484804 (Python Code)

Max Activating Token Index: 9