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

Dataset: The Pile

Neuron 3541 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: 0.3726. Min Range: -0.3726

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1761399 (The Pile)

Max Activating Token Index: 358

Text #1

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1120249 (The Pile)

Max Activating Token Index: 621

Text #2

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2908. Min Act: -0.0000

Data Index: 795524 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2694. Min Act: -0.0000

Data Index: 856584 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1635385 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2558. Min Act: -0.0000

Data Index: 191524 (The Pile)

Max Activating Token Index: 739

Text #6

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2617. Min Act: -0.0000

Data Index: 42783 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2375. Min Act: -0.0000

Data Index: 726709 (The Pile)

Max Activating Token Index: 502

Text #8

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2363. Min Act: -0.0000

Data Index: 657472 (The Pile)

Max Activating Token Index: 171

Text #9

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1669916 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1693293 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2320. Min Act: -0.0000

Data Index: 249573 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1806166 (The Pile)

Max Activating Token Index: 200

Text #13

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1380801 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1325316 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1641768 (The Pile)

Max Activating Token Index: 535

Text #16

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1468648 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2121. Min Act: -0.0000

Data Index: 59764 (The Pile)

Max Activating Token Index: 964

Text #18

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1941642 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2085. Min Act: -0.0000

Data Index: 950668 (The Pile)

Max Activating Token Index: 342