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

Dataset: The Pile

Neuron 4961 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: 3.8766. Min Range: -3.8766

Max Act: 3.8766. Min Act: -0.0000

Data Index: 1008426 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.6698. Min Act: -0.0000

Data Index: 247787 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.4228. Min Act: -0.0000

Data Index: 996775 (The Pile)

Max Activating Token Index: 661

Text #3

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.5006. Min Act: -0.0000

Data Index: 1792618 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.4861. Min Act: -0.0000

Data Index: 1685701 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.4659. Min Act: -0.0000

Data Index: 1509972 (The Pile)

Max Activating Token Index: 867

Text #6

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.4433. Min Act: -0.0000

Data Index: 775797 (The Pile)

Max Activating Token Index: 969

Text #7

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.2714. Min Act: -0.0000

Data Index: 1945331 (The Pile)

Max Activating Token Index: 904

Text #8

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.4088. Min Act: -0.0000

Data Index: 1078580 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.3979. Min Act: -0.0000

Data Index: 1722479 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.3575. Min Act: -0.0000

Data Index: 147436 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.3646. Min Act: -0.0000

Data Index: 258781 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.3565. Min Act: -0.0000

Data Index: 346191 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.3096. Min Act: -0.0000

Data Index: 531752 (The Pile)

Max Activating Token Index: 997

Text #14

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.2955. Min Act: -0.0000

Data Index: 1004741 (The Pile)

Max Activating Token Index: 69

Text #15

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.4513. Min Act: -0.0000

Data Index: 878405 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.3006. Min Act: -0.0000

Data Index: 833387 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.2702. Min Act: -0.0000

Data Index: 1035032 (The Pile)

Max Activating Token Index: 282

Text #18

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.2440. Min Act: -0.0000

Data Index: 272071 (The Pile)

Max Activating Token Index: 555

Text #19

Max Range: 3.8766. Min Range: -3.8766

Max Act: 3.2339. Min Act: -0.0000

Data Index: 1819042 (The Pile)

Max Activating Token Index: 533