Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1475 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.5300. Min Act: -0.0000

Data Index: 790771 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.9475. Min Act: -0.0000

Data Index: 989372 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.9486. Min Act: -0.0000

Data Index: 242553 (The Pile)

Max Activating Token Index: 612

Text #3

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1785826 (The Pile)

Max Activating Token Index: 504

Text #4

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1352400 (The Pile)

Max Activating Token Index: 556

Text #5

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1229632 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1358783 (The Pile)

Max Activating Token Index: 372

Text #7

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.8299. Min Act: -0.0000

Data Index: 888239 (The Pile)

Max Activating Token Index: 243

Text #8

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.7207. Min Act: -0.0000

Data Index: 761554 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.7904. Min Act: -0.0000

Data Index: 667271 (The Pile)

Max Activating Token Index: 807

Text #10

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.6834. Min Act: -0.0000

Data Index: 237778 (The Pile)

Max Activating Token Index: 876

Text #11

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1855809 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1435082 (The Pile)

Max Activating Token Index: 566

Text #13

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.7668. Min Act: -0.0000

Data Index: 702641 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1020429 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.7446. Min Act: -0.0000

Data Index: 209748 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1384679 (The Pile)

Max Activating Token Index: 442

Text #17

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1519009 (The Pile)

Max Activating Token Index: 842

Text #18

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.7702. Min Act: -0.0000

Data Index: 469947 (The Pile)

Max Activating Token Index: 191

Text #19

Max Range: 1.5300. Min Range: -1.5300

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1587561 (The Pile)

Max Activating Token Index: 246