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

Dataset: The Pile

Neuron 3841 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: 4.7684. Min Range: -4.7684

Max Act: 4.7684. Min Act: -0.0000

Data Index: 1479313 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 4.7684. Min Range: -4.7684

Max Act: 4.6862. Min Act: -0.0000

Data Index: 1337654 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.9525. Min Act: -0.0000

Data Index: 347434 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 4.7684. Min Range: -4.7684

Max Act: 4.2077. Min Act: -0.0000

Data Index: 81436 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 4.7684. Min Range: -4.7684

Max Act: 4.3458. Min Act: -0.0000

Data Index: 853298 (The Pile)

Max Activating Token Index: 371

Text #5

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.6854. Min Act: -0.0000

Data Index: 949704 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.7854. Min Act: -0.0000

Data Index: 658488 (The Pile)

Max Activating Token Index: 471

Text #7

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.7274. Min Act: -0.0000

Data Index: 372655 (The Pile)

Max Activating Token Index: 211

Text #8

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.7613. Min Act: -0.0000

Data Index: 306558 (The Pile)

Max Activating Token Index: 954

Text #9

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.7767. Min Act: -0.0000

Data Index: 592699 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.5936. Min Act: -0.0000

Data Index: 1377339 (The Pile)

Max Activating Token Index: 512

Text #11

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.3871. Min Act: -0.0000

Data Index: 878704 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.4576. Min Act: -0.0000

Data Index: 1416574 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.3935. Min Act: -0.0000

Data Index: 1771382 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.5331. Min Act: -0.0000

Data Index: 264174 (The Pile)

Max Activating Token Index: 710

Text #15

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.4576. Min Act: -0.0000

Data Index: 198519 (The Pile)

Max Activating Token Index: 577

Text #16

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.1897. Min Act: 0.0000

Data Index: 1419747 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.2112. Min Act: -0.0000

Data Index: 1628219 (The Pile)

Max Activating Token Index: 697

Text #18

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.1233. Min Act: -0.0000

Data Index: 590144 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 4.7684. Min Range: -4.7684

Max Act: 3.1142. Min Act: -0.0000

Data Index: 1846327 (The Pile)

Max Activating Token Index: 394