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

Dataset: The Pile

Neuron 2311 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: 0.0631. Min Range: -0.0631

Max Act: 0.0631. Min Act: -0.0000

Data Index: 466651 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0627. Min Act: -0.0000

Data Index: 1090505 (The Pile)

Max Activating Token Index: 3

Text #2

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0627. Min Act: 0.0000

Data Index: 1834213 (The Pile)

Max Activating Token Index: 3

Text #3

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0618. Min Act: 0.0000

Data Index: 425314 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1860178 (The Pile)

Max Activating Token Index: 3

Text #5

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0604. Min Act: 0.0000

Data Index: 1288608 (The Pile)

Max Activating Token Index: 3

Text #6

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0601. Min Act: 0.0000

Data Index: 602169 (The Pile)

Max Activating Token Index: 3

Text #7

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0599. Min Act: 0.0000

Data Index: 5929 (The Pile)

Max Activating Token Index: 4

Text #8

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0597. Min Act: 0.0000

Data Index: 1810533 (The Pile)

Max Activating Token Index: 3

Text #9

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0597. Min Act: -0.0000

Data Index: 1731949 (The Pile)

Max Activating Token Index: 3

Text #10

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0594. Min Act: 0.0000

Data Index: 1412712 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0592. Min Act: 0.0000

Data Index: 1096220 (The Pile)

Max Activating Token Index: 3

Text #12

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0567. Min Act: 0.0000

Data Index: 785116 (The Pile)

Max Activating Token Index: 8

Text #13

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0587. Min Act: 0.0000

Data Index: 1536508 (The Pile)

Max Activating Token Index: 3

Text #14

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0587. Min Act: -0.0000

Data Index: 821743 (The Pile)

Max Activating Token Index: 3

Text #15

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0587. Min Act: 0.0000

Data Index: 1354173 (The Pile)

Max Activating Token Index: 3

Text #16

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0588. Min Act: 0.0000

Data Index: 1620115 (The Pile)

Max Activating Token Index: 4

Text #17

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0588. Min Act: -0.0000

Data Index: 275803 (The Pile)

Max Activating Token Index: 3

Text #18

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0588. Min Act: 0.0000

Data Index: 684541 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0588. Min Act: -0.0000

Data Index: 539880 (The Pile)

Max Activating Token Index: 3