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

Dataset: The Pile

Neuron 1522 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: 0.9027. Min Range: -0.9027

Max Act: 0.9027. Min Act: -0.0000

Data Index: 624713 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8993. Min Act: -0.0000

Data Index: 860026 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7901. Min Act: 0.0000

Data Index: 374759 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8665. Min Act: -0.0000

Data Index: 189217 (The Pile)

Max Activating Token Index: 627

Text #4

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7909. Min Act: -0.0000

Data Index: 106498 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1731178 (The Pile)

Max Activating Token Index: 321

Text #6

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7927. Min Act: -0.0000

Data Index: 376148 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1480177 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1432266 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1931258 (The Pile)

Max Activating Token Index: 259

Text #10

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7537. Min Act: -0.0000

Data Index: 374945 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8805. Min Act: -0.0000

Data Index: 473494 (The Pile)

Max Activating Token Index: 877

Text #12

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1766877 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6986. Min Act: -0.0000

Data Index: 212588 (The Pile)

Max Activating Token Index: 878

Text #14

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1328721 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6831. Min Act: -0.0000

Data Index: 901528 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6992. Min Act: -0.0000

Data Index: 370852 (The Pile)

Max Activating Token Index: 549

Text #17

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1746130 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1887799 (The Pile)

Max Activating Token Index: 221

Text #19

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1138926 (The Pile)

Max Activating Token Index: 789