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

Dataset: The Pile

Neuron 1374 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: 1.5941. Min Range: -1.5941

Max Act: 1.5941. Min Act: -0.0000

Data Index: 5684 (The Pile)

Max Activating Token Index: 132

Text #1

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.3954. Min Act: -0.0000

Data Index: 71407 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.2483. Min Act: -0.0000

Data Index: 923480 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1484535 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.0492. Min Act: -0.0000

Data Index: 425117 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.2543. Min Act: -0.0000

Data Index: 1703399 (The Pile)

Max Activating Token Index: 30

Text #6

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.1666. Min Act: -0.0000

Data Index: 212990 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.2099. Min Act: -0.0000

Data Index: 245287 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.0829. Min Act: -0.0000

Data Index: 525202 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1281349 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.0729. Min Act: -0.0000

Data Index: 1385762 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.0242. Min Act: -0.0000

Data Index: 1105425 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 1.5941. Min Range: -1.5941

Max Act: 0.9316. Min Act: -0.0000

Data Index: 678921 (The Pile)

Max Activating Token Index: 211

Text #13

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.0273. Min Act: -0.0000

Data Index: 624194 (The Pile)

Max Activating Token Index: 539

Text #14

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1267943 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 1.5941. Min Range: -1.5941

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1560413 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 1.5941. Min Range: -1.5941

Max Act: 0.9891. Min Act: -0.0000

Data Index: 57788 (The Pile)

Max Activating Token Index: 935

Text #17

Max Range: 1.5941. Min Range: -1.5941

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1640068 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 1.5941. Min Range: -1.5941

Max Act: 0.9919. Min Act: -0.0000

Data Index: 1924955 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 1.5941. Min Range: -1.5941

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1239133 (The Pile)

Max Activating Token Index: 697