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

Dataset: The Pile

Neuron 3960 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: 1.0474. Min Range: -1.0474

Max Act: 1.0474. Min Act: -0.0000

Data Index: 787620 (The Pile)

Max Activating Token Index: 432

Text #1

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9764. Min Act: -0.0000

Data Index: 519580 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1999439 (The Pile)

Max Activating Token Index: 657

Text #3

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1328874 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.8281. Min Act: -0.0000

Data Index: 1420313 (The Pile)

Max Activating Token Index: 47

Text #5

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1076154 (The Pile)

Max Activating Token Index: 556

Text #6

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7429. Min Act: -0.0000

Data Index: 338715 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7298. Min Act: -0.0000

Data Index: 806294 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7362. Min Act: -0.0000

Data Index: 588333 (The Pile)

Max Activating Token Index: 320

Text #9

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.6941. Min Act: -0.0000

Data Index: 931589 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1051978 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1005032 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1693365 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.6954. Min Act: -0.0000

Data Index: 211378 (The Pile)

Max Activating Token Index: 371

Text #14

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7232. Min Act: -0.0000

Data Index: 935241 (The Pile)

Max Activating Token Index: 783

Text #15

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1704424 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.6908. Min Act: -0.0000

Data Index: 825470 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1001110 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1534713 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1727 (The Pile)

Max Activating Token Index: 555