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

Dataset: The Pile

Neuron 2433 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5983. Min Act: 0.0000

Data Index: 422845 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5825. Min Act: -0.0000

Data Index: 988836 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1230454 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1766961 (The Pile)

Max Activating Token Index: 274

Text #4

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5589. Min Act: -0.0000

Data Index: 472981 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1346688 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5478. Min Act: 0.0000

Data Index: 484571 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1584550 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1847172 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5048. Min Act: 0.0000

Data Index: 1713028 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1404314 (The Pile)

Max Activating Token Index: 665

Text #11

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1683889 (The Pile)

Max Activating Token Index: 363

Text #12

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4879. Min Act: 0.0000

Data Index: 805264 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4840. Min Act: -0.0000

Data Index: 549718 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4399. Min Act: 0.0000

Data Index: 16028 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4675. Min Act: 0.0000

Data Index: 640130 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4759. Min Act: -0.0000

Data Index: 383021 (The Pile)

Max Activating Token Index: 753

Text #17

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1630575 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1127982 (The Pile)

Max Activating Token Index: 423

Text #19

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4499. Min Act: 0.0000

Data Index: 1764100 (The Pile)

Max Activating Token Index: 578