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

Dataset: The Pile

Neuron 3782 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: 0.2414. Min Range: -0.2414

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1948593 (The Pile)

Max Activating Token Index: 315

Text #1

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2084. Min Act: -0.0000

Data Index: 236543 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1771. Min Act: -0.0000

Data Index: 451859 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1438589 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1741. Min Act: -0.0000

Data Index: 97489 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1814919 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1733865 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1588341 (The Pile)

Max Activating Token Index: 966

Text #8

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1584. Min Act: -0.0000

Data Index: 1313172 (The Pile)

Max Activating Token Index: 753

Text #9

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1915867 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1513. Min Act: -0.0000

Data Index: 155070 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1554. Min Act: -0.0000

Data Index: 469895 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1512. Min Act: -0.0000

Data Index: 544389 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1602. Min Act: -0.0000

Data Index: 732858 (The Pile)

Max Activating Token Index: 39

Text #14

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1558703 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1857624 (The Pile)

Max Activating Token Index: 464

Text #16

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1329. Min Act: -0.0000

Data Index: 759674 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1525. Min Act: -0.0000

Data Index: 589026 (The Pile)

Max Activating Token Index: 471

Text #18

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1485. Min Act: -0.0000

Data Index: 745230 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1684659 (The Pile)

Max Activating Token Index: 686