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

Dataset: The Pile

Neuron 2165 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1738434 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1555506 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1560038 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4427. Min Act: -0.0000

Data Index: 884697 (The Pile)

Max Activating Token Index: 812

Text #4

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1098277 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3622. Min Act: -0.0000

Data Index: 271203 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1877979 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1536185 (The Pile)

Max Activating Token Index: 293

Text #8

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3827. Min Act: -0.0000

Data Index: 844939 (The Pile)

Max Activating Token Index: 89

Text #9

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3863. Min Act: -0.0000

Data Index: 153639 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4007. Min Act: -0.0000

Data Index: 303633 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1102828 (The Pile)

Max Activating Token Index: 11

Text #12

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3908. Min Act: -0.0000

Data Index: 978009 (The Pile)

Max Activating Token Index: 118

Text #13

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1792682 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1469430 (The Pile)

Max Activating Token Index: 674

Text #15

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1586731 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3805. Min Act: -0.0000

Data Index: 551112 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1680524 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3523. Min Act: -0.0000

Data Index: 460317 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1256337 (The Pile)

Max Activating Token Index: 872