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

Dataset: The Pile

Neuron 3814 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: 3.6349. Min Range: -3.6349

Max Act: 3.6349. Min Act: -0.0000

Data Index: 1966226 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 3.6349. Min Range: -3.6349

Max Act: 3.5682. Min Act: -0.0000

Data Index: 1646465 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 3.6349. Min Range: -3.6349

Max Act: 3.3685. Min Act: -0.0000

Data Index: 1191753 (The Pile)

Max Activating Token Index: 713

Text #3

Max Range: 3.6349. Min Range: -3.6349

Max Act: 3.2024. Min Act: -0.0000

Data Index: 72472 (The Pile)

Max Activating Token Index: 27

Text #4

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.9555. Min Act: -0.0000

Data Index: 900382 (The Pile)

Max Activating Token Index: 808

Text #5

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.6110. Min Act: -0.0000

Data Index: 1637783 (The Pile)

Max Activating Token Index: 863

Text #6

Max Range: 3.6349. Min Range: -3.6349

Max Act: 3.0058. Min Act: -0.0000

Data Index: 1620207 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 3.6349. Min Range: -3.6349

Max Act: 3.1279. Min Act: -0.0000

Data Index: 1301300 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.8237. Min Act: -0.0000

Data Index: 164089 (The Pile)

Max Activating Token Index: 693

Text #9

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.8387. Min Act: -0.0000

Data Index: 597251 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.8211. Min Act: -0.0000

Data Index: 597131 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.6760. Min Act: -0.0000

Data Index: 1350454 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.8065. Min Act: -0.0000

Data Index: 1698435 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.7744. Min Act: -0.0000

Data Index: 1539381 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.7812. Min Act: -0.0000

Data Index: 1928931 (The Pile)

Max Activating Token Index: 48

Text #15

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.4195. Min Act: -0.0000

Data Index: 1872424 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.6713. Min Act: -0.0000

Data Index: 1637313 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.4083. Min Act: -0.0000

Data Index: 1171865 (The Pile)

Max Activating Token Index: 878

Text #18

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.9424. Min Act: -0.0000

Data Index: 1659426 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 3.6349. Min Range: -3.6349

Max Act: 2.5887. Min Act: -0.0000

Data Index: 1749403 (The Pile)

Max Activating Token Index: 34