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

Dataset: The Pile

Neuron 3573 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: 1.3128. Min Range: -1.3128

Max Act: 1.2133. Min Act: -0.0000

Data Index: 1015295 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.3128. Min Act: -0.0000

Data Index: 29008 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.1509. Min Act: -0.0000

Data Index: 247340 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1233213 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0999. Min Act: -0.0000

Data Index: 736620 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9176. Min Act: -0.0000

Data Index: 487953 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.1087. Min Act: -0.0000

Data Index: 243760 (The Pile)

Max Activating Token Index: 655

Text #7

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9670. Min Act: -0.0000

Data Index: 344475 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0377. Min Act: -0.0000

Data Index: 269844 (The Pile)

Max Activating Token Index: 508

Text #9

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0275. Min Act: -0.0000

Data Index: 437657 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0291. Min Act: -0.0000

Data Index: 956899 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1730022 (The Pile)

Max Activating Token Index: 866

Text #12

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1995323 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1621847 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0844. Min Act: -0.0000

Data Index: 113610 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1420853 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1217671 (The Pile)

Max Activating Token Index: 158

Text #17

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0597. Min Act: -0.0000

Data Index: 184639 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9318. Min Act: -0.0000

Data Index: 855560 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9707. Min Act: -0.0000

Data Index: 1378463 (The Pile)

Max Activating Token Index: 851