Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 769 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1800. Min Act: -0.0000

Data Index: 855137 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1374152 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0896. Min Act: -0.0000

Data Index: 147435 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0816. Min Act: -0.0000

Data Index: 681333 (The Pile)

Max Activating Token Index: 737

Text #4

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1783765 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0783. Min Act: -0.0000

Data Index: 502946 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0905. Min Act: -0.0000

Data Index: 426447 (The Pile)

Max Activating Token Index: 262

Text #7

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1656247 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0642. Min Act: -0.0000

Data Index: 554420 (The Pile)

Max Activating Token Index: 911

Text #9

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0693. Min Act: -0.0000

Data Index: 1962089 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0714. Min Act: -0.0000

Data Index: 656777 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1759074 (The Pile)

Max Activating Token Index: 524

Text #12

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1121799 (The Pile)

Max Activating Token Index: 909

Text #13

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0610. Min Act: -0.0000

Data Index: 371936 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0586. Min Act: -0.0000

Data Index: 200002 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1330274 (The Pile)

Max Activating Token Index: 354

Text #16

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0619. Min Act: -0.0000

Data Index: 978074 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0646. Min Act: -0.0000

Data Index: 666847 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1542835 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1664549 (The Pile)

Max Activating Token Index: 941