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

Dataset: The Pile

Neuron 1989 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: 1.6823. Min Range: -1.6823

Max Act: 1.6823. Min Act: -0.0000

Data Index: 740264 (The Pile)

Max Activating Token Index: 673

Text #1

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.5398. Min Act: -0.0000

Data Index: 810750 (The Pile)

Max Activating Token Index: 849

Text #2

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.5513. Min Act: -0.0000

Data Index: 1268943 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4432. Min Act: -0.0000

Data Index: 952972 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4720. Min Act: -0.0000

Data Index: 264684 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4225. Min Act: -0.0000

Data Index: 797204 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4447. Min Act: -0.0000

Data Index: 808982 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1929364 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4060. Min Act: -0.0000

Data Index: 289116 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4030. Min Act: -0.0000

Data Index: 78576 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1956163 (The Pile)

Max Activating Token Index: 892

Text #11

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3470. Min Act: -0.0000

Data Index: 584036 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4103. Min Act: -0.0000

Data Index: 589343 (The Pile)

Max Activating Token Index: 895

Text #13

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3703. Min Act: -0.0000

Data Index: 1604385 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3113. Min Act: -0.0000

Data Index: 1960840 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3540. Min Act: -0.0000

Data Index: 1360682 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3456. Min Act: -0.0000

Data Index: 1981024 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3794. Min Act: -0.0000

Data Index: 1070121 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.2954. Min Act: -0.0000

Data Index: 1716983 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3401. Min Act: -0.0000

Data Index: 1033760 (The Pile)

Max Activating Token Index: 760