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

Dataset: The Pile

Neuron 4807 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2860. Min Act: -0.0000

Data Index: 244881 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1195273 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2134. Min Act: -0.0000

Data Index: 126353 (The Pile)

Max Activating Token Index: 631

Text #3

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1691644 (The Pile)

Max Activating Token Index: 120

Text #4

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1898. Min Act: -0.0000

Data Index: 675688 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1542505 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1807. Min Act: -0.0000

Data Index: 696521 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1871312 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1390839 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1631521 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1627. Min Act: -0.0000

Data Index: 173741 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1577650 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1666. Min Act: -0.0000

Data Index: 330443 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1891857 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1478. Min Act: -0.0000

Data Index: 479517 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1289509 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1394. Min Act: -0.0000

Data Index: 330519 (The Pile)

Max Activating Token Index: 211

Text #17

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1008669 (The Pile)

Max Activating Token Index: 983

Text #18

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1072702 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1683. Min Act: -0.0000

Data Index: 296030 (The Pile)

Max Activating Token Index: 836