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

Dataset: The Pile

Neuron 4410 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: 0.2308. Min Range: -0.2308

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1284463 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1591036 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1389619 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1238799 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1780719 (The Pile)

Max Activating Token Index: 671

Text #5

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1971393 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1903206 (The Pile)

Max Activating Token Index: 494

Text #7

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1498867 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1734598 (The Pile)

Max Activating Token Index: 604

Text #9

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1429. Min Act: -0.0000

Data Index: 41833 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1573. Min Act: -0.0000

Data Index: 428603 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1197197 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1531. Min Act: -0.0000

Data Index: 1813142 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1070449 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1094468 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1087. Min Act: -0.0000

Data Index: 873566 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1019796 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1595. Min Act: -0.0000

Data Index: 238996 (The Pile)

Max Activating Token Index: 394

Text #18

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1614827 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1395. Min Act: -0.0000

Data Index: 485432 (The Pile)

Max Activating Token Index: 817