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

Dataset: The Pile

Neuron 2325 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1571. Min Range: -1.1571

Max Act: 1.1571. Min Act: -0.0000

Data Index: 456013 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 1.1571. Min Range: -1.1571

Max Act: 1.0321. Min Act: -0.0000

Data Index: 473311 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 1.1571. Min Range: -1.1571

Max Act: 1.0255. Min Act: -0.0000

Data Index: 1237656 (The Pile)

Max Activating Token Index: 840

Text #3

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.9506. Min Act: -0.0000

Data Index: 1185444 (The Pile)

Max Activating Token Index: 65

Text #4

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.9572. Min Act: -0.0000

Data Index: 327083 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.9198. Min Act: -0.0000

Data Index: 431333 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.9564. Min Act: -0.0000

Data Index: 622251 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1538123 (The Pile)

Max Activating Token Index: 282

Text #8

Max Range: 1.1571. Min Range: -1.1571

Max Act: 1.0105. Min Act: -0.0000

Data Index: 545090 (The Pile)

Max Activating Token Index: 449

Text #9

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.9747. Min Act: -0.0000

Data Index: 722152 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.9335. Min Act: -0.0000

Data Index: 427425 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.9539. Min Act: -0.0000

Data Index: 461853 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.9417. Min Act: -0.0000

Data Index: 1509546 (The Pile)

Max Activating Token Index: 487

Text #13

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.9333. Min Act: -0.0000

Data Index: 635057 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1056986 (The Pile)

Max Activating Token Index: 923

Text #15

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1749526 (The Pile)

Max Activating Token Index: 126

Text #16

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.9454. Min Act: -0.0000

Data Index: 572696 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.7616. Min Act: -0.0000

Data Index: 935918 (The Pile)

Max Activating Token Index: 75

Text #18

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1494614 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 1.1571. Min Range: -1.1571

Max Act: 0.8684. Min Act: -0.0000

Data Index: 1910452 (The Pile)

Max Activating Token Index: 290