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

Dataset: The Pile

Neuron 4534 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6374. Min Act: -0.0000

Data Index: 918483 (The Pile)

Max Activating Token Index: 363

Text #1

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6605. Min Act: -0.0000

Data Index: 285263 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1711314 (The Pile)

Max Activating Token Index: 542

Text #3

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1869396 (The Pile)

Max Activating Token Index: 112

Text #4

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5400. Min Act: -0.0000

Data Index: 789120 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5025. Min Act: 0.0000

Data Index: 788260 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1051927 (The Pile)

Max Activating Token Index: 177

Text #7

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1826495 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1350198 (The Pile)

Max Activating Token Index: 401

Text #9

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1843185 (The Pile)

Max Activating Token Index: 969

Text #10

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1196736 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1906750 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4635. Min Act: -0.0000

Data Index: 454792 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4616. Min Act: 0.0000

Data Index: 1210274 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4293. Min Act: 0.0000

Data Index: 1073915 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1551302 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1745464 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4180. Min Act: -0.0000

Data Index: 410029 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1932016 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4485. Min Act: -0.0000

Data Index: 268094 (The Pile)

Max Activating Token Index: 608