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

Dataset: The Pile

Neuron 1893 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: 6.9659. Min Range: -6.9659

Max Act: 6.9659. Min Act: -0.0000

Data Index: 1259525 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 6.9659. Min Range: -6.9659

Max Act: 6.2463. Min Act: -0.0000

Data Index: 928579 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 6.9659. Min Range: -6.9659

Max Act: 6.3145. Min Act: -0.0000

Data Index: 226220 (The Pile)

Max Activating Token Index: 202

Text #3

Max Range: 6.9659. Min Range: -6.9659

Max Act: 6.4531. Min Act: -0.0000

Data Index: 1032636 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 6.9659. Min Range: -6.9659

Max Act: 6.4460. Min Act: -0.0000

Data Index: 1247026 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 6.9659. Min Range: -6.9659

Max Act: 6.1009. Min Act: -0.0000

Data Index: 1181161 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 6.9659. Min Range: -6.9659

Max Act: 6.0910. Min Act: -0.0000

Data Index: 1748607 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 6.9659. Min Range: -6.9659

Max Act: 6.0796. Min Act: -0.0000

Data Index: 915710 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 6.9659. Min Range: -6.9659

Max Act: 5.8817. Min Act: -0.0000

Data Index: 1655352 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 6.9659. Min Range: -6.9659

Max Act: 5.6812. Min Act: -0.0000

Data Index: 1485712 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 6.9659. Min Range: -6.9659

Max Act: 5.8620. Min Act: -0.0000

Data Index: 1701903 (The Pile)

Max Activating Token Index: 743

Text #11

Max Range: 6.9659. Min Range: -6.9659

Max Act: 5.8876. Min Act: -0.0000

Data Index: 1014530 (The Pile)

Max Activating Token Index: 747

Text #12

Max Range: 6.9659. Min Range: -6.9659

Max Act: 5.3106. Min Act: -0.0000

Data Index: 108148 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 6.9659. Min Range: -6.9659

Max Act: 6.0403. Min Act: -0.0000

Data Index: 1432404 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 6.9659. Min Range: -6.9659

Max Act: 5.4326. Min Act: -0.0000

Data Index: 606725 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 6.9659. Min Range: -6.9659

Max Act: 5.5771. Min Act: -0.0000

Data Index: 306945 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 6.9659. Min Range: -6.9659

Max Act: 5.8978. Min Act: -0.0000

Data Index: 98078 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 6.9659. Min Range: -6.9659

Max Act: 5.7197. Min Act: -0.0000

Data Index: 1040854 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 6.9659. Min Range: -6.9659

Max Act: 5.6899. Min Act: -0.0000

Data Index: 671019 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 6.9659. Min Range: -6.9659

Max Act: 5.7002. Min Act: -0.0000

Data Index: 1390895 (The Pile)

Max Activating Token Index: 561