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

Dataset: The Pile

Neuron 5008 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4685. Min Act: -0.0000

Data Index: 691196 (The Pile)

Max Activating Token Index: 518

Text #1

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.0071. Min Act: -0.0000

Data Index: 1603214 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.5559. Min Act: -0.0000

Data Index: 237172 (The Pile)

Max Activating Token Index: 393

Text #3

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.3957. Min Act: -0.0000

Data Index: 1148537 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.0455. Min Act: -0.0000

Data Index: 1909072 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 3.5559. Min Range: -3.5559

Max Act: 2.9146. Min Act: -0.0000

Data Index: 1963431 (The Pile)

Max Activating Token Index: 833

Text #6

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.1624. Min Act: -0.0000

Data Index: 1884655 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.2966. Min Act: -0.0000

Data Index: 252500 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 3.5559. Min Range: -3.5559

Max Act: 2.9698. Min Act: -0.0000

Data Index: 490416 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 3.5559. Min Range: -3.5559

Max Act: 2.9614. Min Act: -0.0000

Data Index: 1120982 (The Pile)

Max Activating Token Index: 586

Text #10

Max Range: 3.5559. Min Range: -3.5559

Max Act: 2.9488. Min Act: -0.0000

Data Index: 1492567 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 3.5559. Min Range: -3.5559

Max Act: 2.9420. Min Act: -0.0000

Data Index: 645917 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.0717. Min Act: -0.0000

Data Index: 1637810 (The Pile)

Max Activating Token Index: 734

Text #13

Max Range: 3.5559. Min Range: -3.5559

Max Act: 2.9157. Min Act: -0.0000

Data Index: 433273 (The Pile)

Max Activating Token Index: 880

Text #14

Max Range: 3.5559. Min Range: -3.5559

Max Act: 2.7968. Min Act: -0.0000

Data Index: 1072528 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.3076. Min Act: -0.0000

Data Index: 1069988 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.1405. Min Act: -0.0000

Data Index: 1106654 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 3.5559. Min Range: -3.5559

Max Act: 2.6964. Min Act: -0.0000

Data Index: 1729496 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 3.5559. Min Range: -3.5559

Max Act: 2.8398. Min Act: -0.0000

Data Index: 1383631 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.0378. Min Act: -0.0000

Data Index: 1665953 (The Pile)

Max Activating Token Index: 854