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

Dataset: The Pile

Neuron 864 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.8806. Min Act: -0.0000

Data Index: 870366 (The Pile)

Max Activating Token Index: 515

Text #1

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.6535. Min Act: -0.0000

Data Index: 1211838 (The Pile)

Max Activating Token Index: 46

Text #2

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.7707. Min Act: -0.0000

Data Index: 1877861 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.6226. Min Act: -0.0000

Data Index: 489015 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.5660. Min Act: -0.0000

Data Index: 355319 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.6155. Min Act: -0.0000

Data Index: 1764130 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.6829. Min Act: -0.0000

Data Index: 71942 (The Pile)

Max Activating Token Index: 228

Text #7

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.6799. Min Act: -0.0000

Data Index: 536289 (The Pile)

Max Activating Token Index: 607

Text #8

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.5826. Min Act: -0.0000

Data Index: 1177072 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.5911. Min Act: -0.0000

Data Index: 756859 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1408728 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.3647. Min Act: -0.0000

Data Index: 1271695 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.5205. Min Act: -0.0000

Data Index: 1564485 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.4404. Min Act: -0.0000

Data Index: 1809935 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.5592. Min Act: -0.0000

Data Index: 1472852 (The Pile)

Max Activating Token Index: 935

Text #15

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.3745. Min Act: -0.0000

Data Index: 1448082 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.4578. Min Act: -0.0000

Data Index: 769074 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.3724. Min Act: -0.0000

Data Index: 91467 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.3378. Min Act: -0.0000

Data Index: 261857 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 1.8806. Min Range: -1.8806

Max Act: 1.4091. Min Act: -0.0000

Data Index: 169740 (The Pile)

Max Activating Token Index: 52