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

Dataset: The Pile

Neuron 5022 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.2111. Min Act: -0.0000

Data Index: 462743 (The Pile)

Max Activating Token Index: 40

Text #1

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1812. Min Act: -0.0000

Data Index: 671985 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1745442 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1655621 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1489890 (The Pile)

Max Activating Token Index: 903

Text #5

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1369. Min Act: -0.0000

Data Index: 961869 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1519. Min Act: -0.0000

Data Index: 595949 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1512. Min Act: -0.0000

Data Index: 710462 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1526. Min Act: -0.0000

Data Index: 762058 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1478. Min Act: -0.0000

Data Index: 38080 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1309. Min Act: -0.0000

Data Index: 481939 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1928070 (The Pile)

Max Activating Token Index: 176

Text #12

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1108. Min Act: -0.0000

Data Index: 881458 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1316. Min Act: -0.0000

Data Index: 916880 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1311. Min Act: -0.0000

Data Index: 708948 (The Pile)

Max Activating Token Index: 704

Text #15

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1416. Min Act: -0.0000

Data Index: 913783 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1334244 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1373. Min Act: -0.0000

Data Index: 322145 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1146. Min Act: -0.0000

Data Index: 910158 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1166897 (The Pile)

Max Activating Token Index: 251