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

Dataset: The Pile

Neuron 3531 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0929. Min Range: -1.0929

Max Act: 1.0929. Min Act: -0.0000

Data Index: 276182 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1519591 (The Pile)

Max Activating Token Index: 764

Text #2

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1258904 (The Pile)

Max Activating Token Index: 218

Text #3

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.4161. Min Act: -0.0000

Data Index: 897541 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1039793 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1209472 (The Pile)

Max Activating Token Index: 548

Text #6

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3824. Min Act: -0.0000

Data Index: 678409 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1307841 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3716. Min Act: -0.0000

Data Index: 360126 (The Pile)

Max Activating Token Index: 651

Text #9

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1529264 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1170872 (The Pile)

Max Activating Token Index: 310

Text #11

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1243692 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1132064 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3477. Min Act: -0.0000

Data Index: 592239 (The Pile)

Max Activating Token Index: 377

Text #14

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1966482 (The Pile)

Max Activating Token Index: 204

Text #15

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3010. Min Act: -0.0000

Data Index: 901438 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.2971. Min Act: -0.0000

Data Index: 171734 (The Pile)

Max Activating Token Index: 845

Text #17

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1000928 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.3060. Min Act: -0.0000

Data Index: 875744 (The Pile)

Max Activating Token Index: 847

Text #19

Max Range: 1.0929. Min Range: -1.0929

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1451314 (The Pile)

Max Activating Token Index: 442