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

Dataset: The Pile

Neuron 2659 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: 0.1814. Min Range: -0.1814

Max Act: 0.1725. Min Act: -0.0000

Data Index: 16233 (The Pile)

Max Activating Token Index: 156

Text #1

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1814. Min Act: -0.0000

Data Index: 560153 (The Pile)

Max Activating Token Index: 896

Text #2

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1773. Min Act: -0.0000

Data Index: 450002 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1622. Min Act: -0.0000

Data Index: 729075 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1740. Min Act: -0.0000

Data Index: 803939 (The Pile)

Max Activating Token Index: 122

Text #5

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1633. Min Act: -0.0000

Data Index: 264831 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1318641 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1586647 (The Pile)

Max Activating Token Index: 503

Text #8

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1465393 (The Pile)

Max Activating Token Index: 950

Text #9

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1654. Min Act: -0.0000

Data Index: 746966 (The Pile)

Max Activating Token Index: 702

Text #10

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1585. Min Act: -0.0000

Data Index: 663292 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1505. Min Act: -0.0000

Data Index: 371244 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1486. Min Act: -0.0000

Data Index: 557446 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1497. Min Act: -0.0000

Data Index: 362202 (The Pile)

Max Activating Token Index: 560

Text #14

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1917419 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1552. Min Act: -0.0000

Data Index: 405482 (The Pile)

Max Activating Token Index: 142

Text #16

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1213963 (The Pile)

Max Activating Token Index: 822

Text #17

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1662383 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1699710 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1502. Min Act: -0.0000

Data Index: 517184 (The Pile)

Max Activating Token Index: 410