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

Dataset: The Pile

Neuron 1052 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: 1.2773. Min Range: -1.2773

Max Act: 1.1677. Min Act: -0.0000

Data Index: 76620 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.2773. Min Act: -0.0000

Data Index: 324195 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1485447 (The Pile)

Max Activating Token Index: 903

Text #3

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1621. Min Act: -0.0000

Data Index: 1807847 (The Pile)

Max Activating Token Index: 588

Text #4

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1069754 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1940. Min Act: -0.0000

Data Index: 765645 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1032. Min Act: -0.0000

Data Index: 130599 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1881615 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9408. Min Act: -0.0000

Data Index: 855633 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0536. Min Act: -0.0000

Data Index: 1544702 (The Pile)

Max Activating Token Index: 545

Text #10

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1193. Min Act: -0.0000

Data Index: 1688163 (The Pile)

Max Activating Token Index: 860

Text #11

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0346. Min Act: -0.0000

Data Index: 827432 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9901. Min Act: -0.0000

Data Index: 914712 (The Pile)

Max Activating Token Index: 993

Text #13

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1951554 (The Pile)

Max Activating Token Index: 70

Text #14

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1468977 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1638457 (The Pile)

Max Activating Token Index: 653

Text #16

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9607. Min Act: -0.0000

Data Index: 290923 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1504902 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0640. Min Act: -0.0000

Data Index: 1597727 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0612. Min Act: -0.0000

Data Index: 1497874 (The Pile)

Max Activating Token Index: 594