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

Dataset: The Pile

Neuron 748 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: 0.4927. Min Range: -0.4927

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1382833 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4605. Min Act: -0.0000

Data Index: 435290 (The Pile)

Max Activating Token Index: 950

Text #2

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4449. Min Act: -0.0000

Data Index: 615652 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1026066 (The Pile)

Max Activating Token Index: 588

Text #4

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1516110 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4027. Min Act: -0.0000

Data Index: 571987 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1160888 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3296. Min Act: -0.0000

Data Index: 895910 (The Pile)

Max Activating Token Index: 404

Text #8

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3462. Min Act: -0.0000

Data Index: 294727 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3627. Min Act: -0.0000

Data Index: 680960 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1887268 (The Pile)

Max Activating Token Index: 933

Text #11

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3520. Min Act: -0.0000

Data Index: 656445 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1145032 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3892. Min Act: -0.0000

Data Index: 448862 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1613195 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3465. Min Act: -0.0000

Data Index: 606813 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3132. Min Act: -0.0000

Data Index: 222472 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1143549 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3073. Min Act: -0.0000

Data Index: 897423 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1623134 (The Pile)

Max Activating Token Index: 575