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

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

Neuron 2452 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2389. Min Act: -0.0000

Data Index: 1466552 (Python Code)

Max Activating Token Index: 488

Text #1

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2698. Min Act: -0.0000

Data Index: 1508806 (Python Code)

Max Activating Token Index: 664

Text #2

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.3257. Min Act: -0.0000

Data Index: 1490888 (Python Code)

Max Activating Token Index: 746

Text #3

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1515729 (Python Code)

Max Activating Token Index: 518

Text #4

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1442371 (Python Code)

Max Activating Token Index: 982

Text #5

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1425915 (Python Code)

Max Activating Token Index: 45

Text #6

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0222. Min Act: -0.0000

Data Index: 1487979 (Python Code)

Max Activating Token Index: 298

Text #7

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1641905 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1416. Min Act: -0.0000

Data Index: 482055 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1474886 (Python Code)

Max Activating Token Index: 79

Text #10

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1363943 (Python Code)

Max Activating Token Index: 876

Text #11

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1584703 (Python Code)

Max Activating Token Index: 359

Text #12

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1632891 (Python Code)

Max Activating Token Index: 811

Text #13

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1255. Min Act: -0.0000

Data Index: 1465151 (Python Code)

Max Activating Token Index: 755

Text #14

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1451792 (Python Code)

Max Activating Token Index: 196

Text #15

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1622978 (Python Code)

Max Activating Token Index: 862

Text #16

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0067. Min Act: -0.0000

Data Index: 1383347 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.8290. Min Act: -0.0000

Data Index: 632266 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1399356 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1414617 (Python Code)

Max Activating Token Index: 645