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

Dataset: The Pile

Neuron 650 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: 1.4138. Min Range: -1.4138

Max Act: 1.4138. Min Act: -0.0000

Data Index: 457829 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2570. Min Act: -0.0000

Data Index: 822154 (The Pile)

Max Activating Token Index: 976

Text #2

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1789766 (The Pile)

Max Activating Token Index: 489

Text #3

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1752. Min Act: -0.0000

Data Index: 681352 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1566. Min Act: -0.0000

Data Index: 491395 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1394561 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.0509. Min Act: -0.0000

Data Index: 907639 (The Pile)

Max Activating Token Index: 742

Text #7

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1704. Min Act: -0.0000

Data Index: 1761982 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1484. Min Act: -0.0000

Data Index: 144054 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1350. Min Act: -0.0000

Data Index: 1490030 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1627117 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1492. Min Act: -0.0000

Data Index: 406622 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 1.4138. Min Range: -1.4138

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1807975 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1483313 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1201133 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1922532 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1668. Min Act: -0.0000

Data Index: 1514457 (The Pile)

Max Activating Token Index: 636

Text #17

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.0280. Min Act: -0.0000

Data Index: 1835957 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.0177. Min Act: -0.0000

Data Index: 633815 (The Pile)

Max Activating Token Index: 609

Text #19

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.0849. Min Act: -0.0000

Data Index: 828128 (The Pile)

Max Activating Token Index: 343