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

Dataset: The Pile

Neuron 238 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7327. Min Range: -6.7327

Max Act: 6.7327. Min Act: -0.0000

Data Index: 1028434 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 6.7327. Min Range: -6.7327

Max Act: 6.4536. Min Act: -0.0000

Data Index: 1509913 (The Pile)

Max Activating Token Index: 813

Text #2

Max Range: 6.7327. Min Range: -6.7327

Max Act: 6.3923. Min Act: -0.0000

Data Index: 834237 (The Pile)

Max Activating Token Index: 986

Text #3

Max Range: 6.7327. Min Range: -6.7327

Max Act: 6.1487. Min Act: -0.0000

Data Index: 208452 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 6.7327. Min Range: -6.7327

Max Act: 6.2979. Min Act: -0.0000

Data Index: 1892176 (The Pile)

Max Activating Token Index: 727

Text #5

Max Range: 6.7327. Min Range: -6.7327

Max Act: 5.5713. Min Act: -0.0000

Data Index: 610046 (The Pile)

Max Activating Token Index: 925

Text #6

Max Range: 6.7327. Min Range: -6.7327

Max Act: 6.0155. Min Act: -0.0000

Data Index: 1265679 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 6.7327. Min Range: -6.7327

Max Act: 5.9933. Min Act: -0.0000

Data Index: 1875991 (The Pile)

Max Activating Token Index: 658

Text #8

Max Range: 6.7327. Min Range: -6.7327

Max Act: 6.0981. Min Act: -0.0000

Data Index: 443525 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 6.7327. Min Range: -6.7327

Max Act: 5.8459. Min Act: -0.0000

Data Index: 175889 (The Pile)

Max Activating Token Index: 824

Text #10

Max Range: 6.7327. Min Range: -6.7327

Max Act: 6.0679. Min Act: -0.0000

Data Index: 1390340 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 6.7327. Min Range: -6.7327

Max Act: 5.6908. Min Act: -0.0000

Data Index: 1694106 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 6.7327. Min Range: -6.7327

Max Act: 6.1313. Min Act: -0.0000

Data Index: 1938170 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 6.7327. Min Range: -6.7327

Max Act: 5.8655. Min Act: -0.0000

Data Index: 1859009 (The Pile)

Max Activating Token Index: 903

Text #14

Max Range: 6.7327. Min Range: -6.7327

Max Act: 6.1183. Min Act: -0.0000

Data Index: 946863 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 6.7327. Min Range: -6.7327

Max Act: 6.1549. Min Act: -0.0000

Data Index: 404208 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 6.7327. Min Range: -6.7327

Max Act: 5.9075. Min Act: -0.0000

Data Index: 895310 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 6.7327. Min Range: -6.7327

Max Act: 5.5944. Min Act: -0.0000

Data Index: 1072454 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 6.7327. Min Range: -6.7327

Max Act: 5.7882. Min Act: -0.0000

Data Index: 462918 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 6.7327. Min Range: -6.7327

Max Act: 5.7801. Min Act: -0.0000

Data Index: 1609060 (The Pile)

Max Activating Token Index: 873