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

Dataset: The Pile

Neuron 58 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1903. Min Act: -0.0000

Data Index: 428832 (The Pile)

Max Activating Token Index: 508

Text #1

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1774. Min Act: -0.0000

Data Index: 128960 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1807545 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1461380 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1926. Min Act: -0.0000

Data Index: 709989 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1675991 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1745. Min Act: 0.0000

Data Index: 1294348 (The Pile)

Max Activating Token Index: 689

Text #7

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1733. Min Act: -0.0000

Data Index: 389749 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1660. Min Act: -0.0000

Data Index: 462141 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1710. Min Act: 0.0000

Data Index: 351788 (The Pile)

Max Activating Token Index: 66

Text #10

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1170506 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1647. Min Act: -0.0000

Data Index: 797731 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1078920 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1843231 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1777194 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1652. Min Act: -0.0000

Data Index: 1152440 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1624. Min Act: -0.0000

Data Index: 7380 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1254518 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1578344 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1643. Min Act: -0.0000

Data Index: 186036 (The Pile)

Max Activating Token Index: 327