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

Dataset: The Pile

Neuron 3715 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0966. Min Act: -0.0000

Data Index: 227859 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0949. Min Act: -0.0000

Data Index: 910962 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1753212 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1438283 (The Pile)

Max Activating Token Index: 785

Text #4

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1006321 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1102490 (The Pile)

Max Activating Token Index: 448

Text #6

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1715801 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1682874 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0727. Min Act: -0.0000

Data Index: 844186 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1845333 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1485831 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1243677 (The Pile)

Max Activating Token Index: 347

Text #12

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0687. Min Act: -0.0000

Data Index: 206491 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0662. Min Act: -0.0000

Data Index: 736913 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0681. Min Act: -0.0000

Data Index: 91835 (The Pile)

Max Activating Token Index: 755

Text #15

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0656. Min Act: -0.0000

Data Index: 248680 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0686. Min Act: -0.0000

Data Index: 850642 (The Pile)

Max Activating Token Index: 505

Text #17

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0668. Min Act: -0.0000

Data Index: 727022 (The Pile)

Max Activating Token Index: 963

Text #18

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0668. Min Act: -0.0000

Data Index: 709627 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1264178 (The Pile)

Max Activating Token Index: 1023