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

Dataset: The Pile

Neuron 1014 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3505. Min Range: -5.3505

Max Act: 5.3505. Min Act: -0.0000

Data Index: 1575683 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 5.3505. Min Range: -5.3505

Max Act: 4.3924. Min Act: -0.0000

Data Index: 1777940 (The Pile)

Max Activating Token Index: 705

Text #2

Max Range: 5.3505. Min Range: -5.3505

Max Act: 4.5103. Min Act: -0.0000

Data Index: 900616 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 5.3505. Min Range: -5.3505

Max Act: 3.8436. Min Act: -0.0000

Data Index: 1557388 (The Pile)

Max Activating Token Index: 813

Text #4

Max Range: 5.3505. Min Range: -5.3505

Max Act: 4.1018. Min Act: -0.0000

Data Index: 912836 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 5.3505. Min Range: -5.3505

Max Act: 4.2035. Min Act: -0.0000

Data Index: 398851 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 5.3505. Min Range: -5.3505

Max Act: 4.2613. Min Act: -0.0000

Data Index: 1221279 (The Pile)

Max Activating Token Index: 742

Text #7

Max Range: 5.3505. Min Range: -5.3505

Max Act: 4.2061. Min Act: -0.0000

Data Index: 1902989 (The Pile)

Max Activating Token Index: 567

Text #8

Max Range: 5.3505. Min Range: -5.3505

Max Act: 4.1394. Min Act: -0.0000

Data Index: 524564 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 5.3505. Min Range: -5.3505

Max Act: 3.7025. Min Act: -0.0000

Data Index: 557063 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 5.3505. Min Range: -5.3505

Max Act: 3.8547. Min Act: -0.0000

Data Index: 46799 (The Pile)

Max Activating Token Index: 518

Text #11

Max Range: 5.3505. Min Range: -5.3505

Max Act: 3.6770. Min Act: -0.0000

Data Index: 511815 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 5.3505. Min Range: -5.3505

Max Act: 4.1095. Min Act: -0.0000

Data Index: 354637 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 5.3505. Min Range: -5.3505

Max Act: 3.6801. Min Act: -0.0000

Data Index: 1429625 (The Pile)

Max Activating Token Index: 804

Text #14

Max Range: 5.3505. Min Range: -5.3505

Max Act: 3.8627. Min Act: -0.0000

Data Index: 858007 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 5.3505. Min Range: -5.3505

Max Act: 3.7084. Min Act: -0.0000

Data Index: 1904141 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 5.3505. Min Range: -5.3505

Max Act: 3.4584. Min Act: -0.0000

Data Index: 388769 (The Pile)

Max Activating Token Index: 832

Text #17

Max Range: 5.3505. Min Range: -5.3505

Max Act: 3.6099. Min Act: -0.0000

Data Index: 663495 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 5.3505. Min Range: -5.3505

Max Act: 3.7328. Min Act: -0.0000

Data Index: 299673 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 5.3505. Min Range: -5.3505

Max Act: 3.7297. Min Act: -0.0000

Data Index: 218175 (The Pile)

Max Activating Token Index: 768