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

Dataset: The Pile

Neuron 3939 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: 0.1159. Min Range: -0.1159

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1147416 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1488616 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1970703 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1121. Min Act: -0.0000

Data Index: 343330 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1154731 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1501195 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0960. Min Act: -0.0000

Data Index: 699862 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0985. Min Act: -0.0000

Data Index: 602588 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0932. Min Act: -0.0000

Data Index: 368905 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1026064 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0762. Min Act: -0.0000

Data Index: 271357 (The Pile)

Max Activating Token Index: 907

Text #11

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1802322 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0834. Min Act: -0.0000

Data Index: 821497 (The Pile)

Max Activating Token Index: 768

Text #13

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0848. Min Act: -0.0000

Data Index: 451771 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1425569 (The Pile)

Max Activating Token Index: 861

Text #15

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0905. Min Act: -0.0000

Data Index: 688417 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0786. Min Act: -0.0000

Data Index: 572392 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0650. Min Act: -0.0000

Data Index: 670917 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0850. Min Act: -0.0000

Data Index: 343128 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0698. Min Act: -0.0000

Data Index: 762374 (The Pile)

Max Activating Token Index: 683