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

Dataset: The Pile

Neuron 960 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: 0.5701. Min Range: -0.5701

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1198769 (The Pile)

Max Activating Token Index: 722

Text #1

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1867363 (The Pile)

Max Activating Token Index: 666

Text #2

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1623577 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1621533 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1546646 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1856470 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1561939 (The Pile)

Max Activating Token Index: 47

Text #7

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4419. Min Act: -0.0000

Data Index: 616459 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4265. Min Act: -0.0000

Data Index: 523975 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1419053 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1010116 (The Pile)

Max Activating Token Index: 592

Text #11

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4006. Min Act: -0.0000

Data Index: 176907 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3924. Min Act: -0.0000

Data Index: 161834 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1882268 (The Pile)

Max Activating Token Index: 756

Text #14

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3688. Min Act: -0.0000

Data Index: 268037 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1261720 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1936985 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1077915 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1817326 (The Pile)

Max Activating Token Index: 419

Text #19

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3343. Min Act: -0.0000

Data Index: 705135 (The Pile)

Max Activating Token Index: 383