Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1622 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2659. Min Act: -0.0000

Data Index: 402557 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1157262 (The Pile)

Max Activating Token Index: 860

Text #2

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1851544 (The Pile)

Max Activating Token Index: 1002

Text #3

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1798. Min Act: -0.0000

Data Index: 443056 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1806061 (The Pile)

Max Activating Token Index: 817

Text #5

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1768. Min Act: -0.0000

Data Index: 30982 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1641. Min Act: -0.0000

Data Index: 404528 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1581. Min Act: -0.0000

Data Index: 639034 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1564. Min Act: -0.0000

Data Index: 915441 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1587. Min Act: -0.0000

Data Index: 593909 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1022733 (The Pile)

Max Activating Token Index: 696

Text #11

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1045319 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1449385 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1343200 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1474. Min Act: -0.0000

Data Index: 572298 (The Pile)

Max Activating Token Index: 504

Text #15

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1843706 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1388. Min Act: -0.0000

Data Index: 95955 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1688142 (The Pile)

Max Activating Token Index: 201

Text #18

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1465. Min Act: -0.0000

Data Index: 801511 (The Pile)

Max Activating Token Index: 219

Text #19

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1779339 (The Pile)

Max Activating Token Index: 26