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

Dataset: The Pile

Neuron 525 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.9334. Min Act: -0.0000

Data Index: 1061561 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7892. Min Act: -0.0000

Data Index: 650798 (The Pile)

Max Activating Token Index: 595

Text #2

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.8762. Min Act: -0.0000

Data Index: 1655593 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7662. Min Act: -0.0000

Data Index: 1554938 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.8499. Min Act: -0.0000

Data Index: 966228 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7363. Min Act: -0.0000

Data Index: 368272 (The Pile)

Max Activating Token Index: 650

Text #6

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7354. Min Act: -0.0000

Data Index: 35294 (The Pile)

Max Activating Token Index: 533

Text #7

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7272. Min Act: -0.0000

Data Index: 641666 (The Pile)

Max Activating Token Index: 572

Text #8

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.8299. Min Act: -0.0000

Data Index: 427449 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.8202. Min Act: -0.0000

Data Index: 1487858 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7994. Min Act: -0.0000

Data Index: 1736850 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.8142. Min Act: -0.0000

Data Index: 427489 (The Pile)

Max Activating Token Index: 742

Text #12

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.8088. Min Act: -0.0000

Data Index: 1055906 (The Pile)

Max Activating Token Index: 631

Text #13

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7989. Min Act: -0.0000

Data Index: 1235610 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.8089. Min Act: -0.0000

Data Index: 1856135 (The Pile)

Max Activating Token Index: 744

Text #15

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.8973. Min Act: -0.0000

Data Index: 1186655 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7936. Min Act: -0.0000

Data Index: 495046 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.7039. Min Act: -0.0000

Data Index: 1917759 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.6814. Min Act: -0.0000

Data Index: 665513 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 1.9334. Min Range: -1.9334

Max Act: 1.8827. Min Act: -0.0000

Data Index: 625406 (The Pile)

Max Activating Token Index: 825