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

Dataset: The Pile

Neuron 1599 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: 1.1710. Min Range: -1.1710

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1301311 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 1.1710. Min Range: -1.1710

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1726240 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 1.1710. Min Range: -1.1710

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1882737 (The Pile)

Max Activating Token Index: 252

Text #3

Max Range: 1.1710. Min Range: -1.1710

Max Act: 1.0610. Min Act: -0.0000

Data Index: 543538 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8395. Min Act: -0.0000

Data Index: 698708 (The Pile)

Max Activating Token Index: 954

Text #5

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1543769 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8833. Min Act: -0.0000

Data Index: 1450980 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8881. Min Act: -0.0000

Data Index: 585587 (The Pile)

Max Activating Token Index: 764

Text #8

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.6419. Min Act: -0.0000

Data Index: 393476 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8690. Min Act: -0.0000

Data Index: 183502 (The Pile)

Max Activating Token Index: 460

Text #10

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1161112 (The Pile)

Max Activating Token Index: 740

Text #11

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1190185 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.7012. Min Act: -0.0000

Data Index: 967145 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8067. Min Act: -0.0000

Data Index: 167294 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8049. Min Act: -0.0000

Data Index: 735223 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8459. Min Act: -0.0000

Data Index: 1185907 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8275. Min Act: -0.0000

Data Index: 148526 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.7575. Min Act: -0.0000

Data Index: 748391 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1475288 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.7652. Min Act: -0.0000

Data Index: 518810 (The Pile)

Max Activating Token Index: 676