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

Dataset: The Pile

Neuron 2090 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.9203. Min Act: -0.0000

Data Index: 445336 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1446678 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8909. Min Act: -0.0000

Data Index: 620824 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7607. Min Act: -0.0000

Data Index: 73252 (The Pile)

Max Activating Token Index: 563

Text #4

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1457571 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1007156 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8040. Min Act: -0.0000

Data Index: 556918 (The Pile)

Max Activating Token Index: 392

Text #7

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.6044. Min Act: -0.0000

Data Index: 135232 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.6127. Min Act: -0.0000

Data Index: 486482 (The Pile)

Max Activating Token Index: 671

Text #9

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.6551. Min Act: -0.0000

Data Index: 592779 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.5910. Min Act: -0.0000

Data Index: 278883 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1254847 (The Pile)

Max Activating Token Index: 640

Text #12

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.5712. Min Act: -0.0000

Data Index: 257342 (The Pile)

Max Activating Token Index: 380

Text #13

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1775967 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.5150. Min Act: -0.0000

Data Index: 992510 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.5079. Min Act: -0.0000

Data Index: 301765 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1839203 (The Pile)

Max Activating Token Index: 746

Text #17

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.5644. Min Act: -0.0000

Data Index: 847697 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1866374 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.5399. Min Act: -0.0000

Data Index: 754826 (The Pile)

Max Activating Token Index: 744