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

Dataset: The Pile

Neuron 4118 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.4868. Min Act: -0.0000

Data Index: 1695893 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.1629. Min Act: -0.0000

Data Index: 629555 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1786827 (The Pile)

Max Activating Token Index: 467

Text #3

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.9660. Min Act: -0.0000

Data Index: 359091 (The Pile)

Max Activating Token Index: 658

Text #4

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1259636 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.9886. Min Act: -0.0000

Data Index: 835942 (The Pile)

Max Activating Token Index: 380

Text #6

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1911302 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1449527 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.0196. Min Act: -0.0000

Data Index: 6521 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 1.4868. Min Range: -1.4868

Max Act: 1.0241. Min Act: -0.0000

Data Index: 66000 (The Pile)

Max Activating Token Index: 609

Text #10

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.9825. Min Act: -0.0000

Data Index: 1787638 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.9862. Min Act: -0.0000

Data Index: 918425 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.9581. Min Act: -0.0000

Data Index: 763258 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1851857 (The Pile)

Max Activating Token Index: 343

Text #14

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.9542. Min Act: -0.0000

Data Index: 443999 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1777644 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1751063 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.9829. Min Act: -0.0000

Data Index: 482817 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1932567 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 1.4868. Min Range: -1.4868

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1050554 (The Pile)

Max Activating Token Index: 793