Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1215 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1760289 (The Pile)

Max Activating Token Index: 691

Text #1

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1271914 (The Pile)

Max Activating Token Index: 891

Text #2

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1146819 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5669. Min Act: -0.0000

Data Index: 897105 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1235679 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5776. Min Act: -0.0000

Data Index: 292741 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1084466 (The Pile)

Max Activating Token Index: 777

Text #7

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1002900 (The Pile)

Max Activating Token Index: 448

Text #8

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1543825 (The Pile)

Max Activating Token Index: 437

Text #9

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.4976. Min Act: -0.0000

Data Index: 567691 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.4965. Min Act: -0.0000

Data Index: 905105 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5134. Min Act: -0.0000

Data Index: 405083 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1113506 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.4749. Min Act: -0.0000

Data Index: 675939 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5078. Min Act: -0.0000

Data Index: 999051 (The Pile)

Max Activating Token Index: 798

Text #15

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.4828. Min Act: -0.0000

Data Index: 127162 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.4428. Min Act: -0.0000

Data Index: 89055 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1727021 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1090449 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.4711. Min Act: -0.0000

Data Index: 870857 (The Pile)

Max Activating Token Index: 948