Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2928 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1828. Min Act: -0.0001

Data Index: 852082 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1810. Min Act: -0.0001

Data Index: 585033 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1616123 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1653. Min Act: -0.0001

Data Index: 343932 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1025250 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1734. Min Act: -0.0001

Data Index: 673358 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1647. Min Act: -0.0001

Data Index: 637547 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1653. Min Act: -0.0001

Data Index: 236883 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1650. Min Act: -0.0001

Data Index: 924233 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1620. Min Act: -0.0001

Data Index: 986527 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1557. Min Act: -0.0001

Data Index: 242389 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1057946 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1589. Min Act: -0.0001

Data Index: 451967 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1578. Min Act: -0.0001

Data Index: 115226 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1242915 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1522. Min Act: -0.0001

Data Index: 446710 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1093483 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1494. Min Act: -0.0001

Data Index: 775416 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1473. Min Act: -0.0001

Data Index: 972945 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.1828. Min Range: -0.1828

Max Act: 0.1500. Min Act: -0.0001

Data Index: 887876 (C4 (Web Text))

Max Activating Token Index: 1022