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

Dataset: The Pile

Neuron 2997 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: 0.5820. Min Range: -0.5820

Max Act: 0.5820. Min Act: 0.0000

Data Index: 1799255 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5483. Min Act: -0.0000

Data Index: 893677 (The Pile)

Max Activating Token Index: 267

Text #2

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4846. Min Act: -0.0000

Data Index: 726361 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5467. Min Act: -0.0000

Data Index: 95689 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1722050 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1243204 (The Pile)

Max Activating Token Index: 204

Text #6

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1834265 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4755. Min Act: 0.0000

Data Index: 954829 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1932895 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1790616 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4697. Min Act: 0.0000

Data Index: 902039 (The Pile)

Max Activating Token Index: 226

Text #11

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4462. Min Act: -0.0000

Data Index: 181344 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4568. Min Act: -0.0000

Data Index: 984594 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1043691 (The Pile)

Max Activating Token Index: 725

Text #14

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1317335 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4399. Min Act: -0.0000

Data Index: 460190 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4215. Min Act: -0.0000

Data Index: 641981 (The Pile)

Max Activating Token Index: 518

Text #17

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4358. Min Act: -0.0000

Data Index: 666387 (The Pile)

Max Activating Token Index: 968

Text #18

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1058782 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1690649 (The Pile)

Max Activating Token Index: 756