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

Dataset: The Pile

Neuron 4044 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: 0.5908. Min Range: -0.5908

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1201942 (The Pile)

Max Activating Token Index: 533

Text #1

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.5833. Min Act: -0.0000

Data Index: 201412 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.5678. Min Act: -0.0000

Data Index: 509490 (The Pile)

Max Activating Token Index: 542

Text #3

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1612534 (The Pile)

Max Activating Token Index: 1000

Text #4

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4931. Min Act: -0.0000

Data Index: 562151 (The Pile)

Max Activating Token Index: 493

Text #5

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1271550 (The Pile)

Max Activating Token Index: 571

Text #6

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4574. Min Act: -0.0000

Data Index: 178097 (The Pile)

Max Activating Token Index: 371

Text #7

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1889437 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4985. Min Act: -0.0000

Data Index: 803232 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4005. Min Act: -0.0000

Data Index: 372912 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1766635 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1031364 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1749426 (The Pile)

Max Activating Token Index: 991

Text #13

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4478. Min Act: -0.0000

Data Index: 918986 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4248. Min Act: -0.0000

Data Index: 3615 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1963785 (The Pile)

Max Activating Token Index: 383

Text #16

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4696. Min Act: -0.0000

Data Index: 364688 (The Pile)

Max Activating Token Index: 266

Text #17

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4366. Min Act: -0.0000

Data Index: 362976 (The Pile)

Max Activating Token Index: 815

Text #18

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4390. Min Act: -0.0000

Data Index: 590871 (The Pile)

Max Activating Token Index: 436

Text #19

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1324383 (The Pile)

Max Activating Token Index: 677