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

Dataset: The Pile

Neuron 463 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6965. Min Range: -5.6965

Max Act: 5.6965. Min Act: -0.0000

Data Index: 1509909 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 5.6965. Min Range: -5.6965

Max Act: 5.6965. Min Act: -0.0000

Data Index: 90740 (The Pile)

Max Activating Token Index: 5

Text #2

Max Range: 5.6965. Min Range: -5.6965

Max Act: 5.1738. Min Act: -0.0000

Data Index: 834802 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.7306. Min Act: -0.0000

Data Index: 1881023 (The Pile)

Max Activating Token Index: 690

Text #4

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.8889. Min Act: 0.0000

Data Index: 7858 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.4087. Min Act: -0.0000

Data Index: 991261 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 5.6965. Min Range: -5.6965

Max Act: 5.1639. Min Act: -0.0000

Data Index: 877280 (The Pile)

Max Activating Token Index: 905

Text #7

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.9815. Min Act: -0.0000

Data Index: 50668 (The Pile)

Max Activating Token Index: 909

Text #8

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.8896. Min Act: -0.0000

Data Index: 461574 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.3483. Min Act: -0.0000

Data Index: 1986021 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.7283. Min Act: -0.0000

Data Index: 1401524 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.8529. Min Act: -0.0000

Data Index: 1619738 (The Pile)

Max Activating Token Index: 801

Text #12

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.6597. Min Act: -0.0000

Data Index: 1731988 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 5.6965. Min Range: -5.6965

Max Act: 5.0595. Min Act: -0.0000

Data Index: 1738050 (The Pile)

Max Activating Token Index: 682

Text #14

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.8368. Min Act: -0.0000

Data Index: 1384182 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.6240. Min Act: -0.0000

Data Index: 1629258 (The Pile)

Max Activating Token Index: 892

Text #16

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.7669. Min Act: -0.0000

Data Index: 435741 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.5774. Min Act: -0.0000

Data Index: 1959045 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.5818. Min Act: -0.0000

Data Index: 46970 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 5.6965. Min Range: -5.6965

Max Act: 4.7754. Min Act: -0.0000

Data Index: 1838830 (The Pile)

Max Activating Token Index: 8