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

Dataset: The Pile

Neuron 3054 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1438843 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.8020. Min Act: -0.0000

Data Index: 582629 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.7399. Min Act: -0.0000

Data Index: 760200 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6534. Min Act: -0.0000

Data Index: 781037 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1907437 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6667. Min Act: -0.0000

Data Index: 257814 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6699. Min Act: -0.0000

Data Index: 189283 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1025862 (The Pile)

Max Activating Token Index: 493

Text #8

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1321879 (The Pile)

Max Activating Token Index: 710

Text #9

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1839421 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1491844 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6364. Min Act: -0.0000

Data Index: 773862 (The Pile)

Max Activating Token Index: 560

Text #12

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1803519 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.5866. Min Act: -0.0000

Data Index: 333759 (The Pile)

Max Activating Token Index: 366

Text #14

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6041. Min Act: -0.0000

Data Index: 724101 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1443561 (The Pile)

Max Activating Token Index: 800

Text #16

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1850933 (The Pile)

Max Activating Token Index: 312

Text #17

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1731220 (The Pile)

Max Activating Token Index: 261

Text #18

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1047385 (The Pile)

Max Activating Token Index: 440

Text #19

Max Range: 0.8385. Min Range: -0.8385

Max Act: 0.6267. Min Act: -0.0000

Data Index: 655075 (The Pile)

Max Activating Token Index: 295