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

Dataset: The Pile

Neuron 3459 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1669473 (The Pile)

Max Activating Token Index: 376

Text #1

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1176764 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0868. Min Act: -0.0000

Data Index: 836530 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0794. Min Act: -0.0000

Data Index: 25210 (The Pile)

Max Activating Token Index: 918

Text #4

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1104044 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0800. Min Act: -0.0000

Data Index: 834790 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0844. Min Act: -0.0000

Data Index: 876909 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0747. Min Act: -0.0000

Data Index: 429782 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0756. Min Act: -0.0000

Data Index: 32192 (The Pile)

Max Activating Token Index: 724

Text #9

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1398127 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0666. Min Act: -0.0000

Data Index: 363255 (The Pile)

Max Activating Token Index: 858

Text #11

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1369895 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0728. Min Act: -0.0000

Data Index: 695080 (The Pile)

Max Activating Token Index: 531

Text #13

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0713. Min Act: -0.0000

Data Index: 1527972 (The Pile)

Max Activating Token Index: 420

Text #14

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0600. Min Act: -0.0000

Data Index: 330600 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0698. Min Act: -0.0000

Data Index: 741788 (The Pile)

Max Activating Token Index: 872

Text #16

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1934809 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1314409 (The Pile)

Max Activating Token Index: 947

Text #18

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1172856 (The Pile)

Max Activating Token Index: 940

Text #19

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1304003 (The Pile)

Max Activating Token Index: 64