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

Dataset: The Pile

Neuron 1344 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1827285 (The Pile)

Max Activating Token Index: 567

Text #1

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1235175 (The Pile)

Max Activating Token Index: 663

Text #2

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1781005 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1581094 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9265. Min Act: -0.0000

Data Index: 383606 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1677959 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1235425 (The Pile)

Max Activating Token Index: 337

Text #7

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1102603 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1649696 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1133430 (The Pile)

Max Activating Token Index: 245

Text #10

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8426. Min Act: -0.0000

Data Index: 229500 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1416578 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1786131 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7717. Min Act: -0.0000

Data Index: 819131 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8017. Min Act: -0.0000

Data Index: 741890 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7882. Min Act: -0.0000

Data Index: 815735 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7878. Min Act: -0.0000

Data Index: 58176 (The Pile)

Max Activating Token Index: 63

Text #17

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1921621 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1751386 (The Pile)

Max Activating Token Index: 313

Text #19

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1452553 (The Pile)

Max Activating Token Index: 631