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

Dataset: The Pile

Neuron 678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1045721 (The Pile)

Max Activating Token Index: 560

Text #1

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5920. Min Act: -0.0000

Data Index: 282784 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5720. Min Act: -0.0000

Data Index: 578570 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1337234 (The Pile)

Max Activating Token Index: 981

Text #4

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1544695 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5438. Min Act: 0.0000

Data Index: 91764 (The Pile)

Max Activating Token Index: 368

Text #6

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1281375 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1854537 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5127. Min Act: 0.0000

Data Index: 419381 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5287. Min Act: -0.0000

Data Index: 967641 (The Pile)

Max Activating Token Index: 969

Text #10

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1667331 (The Pile)

Max Activating Token Index: 901

Text #11

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4891. Min Act: 0.0000

Data Index: 1262296 (The Pile)

Max Activating Token Index: 676

Text #12

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4846. Min Act: -0.0000

Data Index: 726071 (The Pile)

Max Activating Token Index: 759

Text #13

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4826. Min Act: -0.0000

Data Index: 959677 (The Pile)

Max Activating Token Index: 657

Text #14

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4705. Min Act: -0.0000

Data Index: 105532 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1350377 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4688. Min Act: -0.0000

Data Index: 617362 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4946. Min Act: -0.0000

Data Index: 787196 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4613. Min Act: -0.0000

Data Index: 434808 (The Pile)

Max Activating Token Index: 692

Text #19

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1023369 (The Pile)

Max Activating Token Index: 603