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

Dataset: The Pile

Neuron 3142 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7945. Min Act: -0.0000

Data Index: 193066 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7628. Min Act: -0.0000

Data Index: 485681 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1571013 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1901088 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6669. Min Act: -0.0000

Data Index: 855851 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6202. Min Act: -0.0000

Data Index: 869457 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6538. Min Act: -0.0000

Data Index: 887661 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1911445 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6231. Min Act: -0.0000

Data Index: 467786 (The Pile)

Max Activating Token Index: 211

Text #9

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5901. Min Act: -0.0000

Data Index: 875739 (The Pile)

Max Activating Token Index: 441

Text #10

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5625. Min Act: -0.0000

Data Index: 661417 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5357. Min Act: -0.0000

Data Index: 801369 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5519. Min Act: -0.0000

Data Index: 1889314 (The Pile)

Max Activating Token Index: 422

Text #13

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5642. Min Act: -0.0000

Data Index: 426189 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1270918 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.4998. Min Act: -0.0000

Data Index: 699 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5095. Min Act: -0.0000

Data Index: 499249 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5041. Min Act: -0.0000

Data Index: 527416 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.4961. Min Act: -0.0000

Data Index: 66104 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1535296 (The Pile)

Max Activating Token Index: 581