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

Dataset: The Pile

Neuron 2528 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: 0.4637. Min Range: -0.4637

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1740489 (The Pile)

Max Activating Token Index: 693

Text #1

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4343. Min Act: -0.0000

Data Index: 466928 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4001. Min Act: -0.0000

Data Index: 522318 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3651. Min Act: -0.0000

Data Index: 387954 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1589504 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1155250 (The Pile)

Max Activating Token Index: 810

Text #6

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1700131 (The Pile)

Max Activating Token Index: 921

Text #7

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1423563 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2988. Min Act: -0.0000

Data Index: 713663 (The Pile)

Max Activating Token Index: 961

Text #9

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3695. Min Act: -0.0000

Data Index: 80472 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1937879 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3169. Min Act: -0.0000

Data Index: 756348 (The Pile)

Max Activating Token Index: 598

Text #12

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1727300 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1458474 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1928200 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2804. Min Act: -0.0000

Data Index: 539052 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1688110 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2730. Min Act: -0.0000

Data Index: 559223 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2586. Min Act: -0.0000

Data Index: 501295 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.2655. Min Act: -0.0000

Data Index: 802834 (The Pile)

Max Activating Token Index: 13