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

Dataset: The Pile

Neuron 1969 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: 0.1960. Min Range: -0.1960

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1510384 (The Pile)

Max Activating Token Index: 875

Text #1

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1404888 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1836794 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1600068 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1736. Min Act: -0.0000

Data Index: 283189 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1500870 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1580. Min Act: -0.0000

Data Index: 339712 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1457264 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1622. Min Act: -0.0000

Data Index: 781215 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1481453 (The Pile)

Max Activating Token Index: 428

Text #10

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1621. Min Act: -0.0000

Data Index: 36788 (The Pile)

Max Activating Token Index: 405

Text #11

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1515. Min Act: -0.0000

Data Index: 774138 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1881381 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1518146 (The Pile)

Max Activating Token Index: 588

Text #14

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1232149 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1456. Min Act: -0.0000

Data Index: 990456 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1658793 (The Pile)

Max Activating Token Index: 182

Text #17

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1494078 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1693047 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1434. Min Act: -0.0000

Data Index: 188192 (The Pile)

Max Activating Token Index: 1008