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

Dataset: The Pile

Neuron 3632 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1251005 (The Pile)

Max Activating Token Index: 944

Text #1

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3093. Min Act: -0.0000

Data Index: 745505 (The Pile)

Max Activating Token Index: 454

Text #2

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1212303 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3046. Min Act: -0.0000

Data Index: 265126 (The Pile)

Max Activating Token Index: 460

Text #4

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1218058 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2575. Min Act: -0.0000

Data Index: 977875 (The Pile)

Max Activating Token Index: 713

Text #6

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1479723 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1278599 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1556723 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1258875 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1115766 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1533147 (The Pile)

Max Activating Token Index: 314

Text #12

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1779. Min Act: -0.0000

Data Index: 385056 (The Pile)

Max Activating Token Index: 553

Text #13

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1926. Min Act: -0.0000

Data Index: 863259 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1010038 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1604878 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1864. Min Act: -0.0000

Data Index: 308953 (The Pile)

Max Activating Token Index: 414

Text #17

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1696805 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1358727 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1474484 (The Pile)

Max Activating Token Index: 977