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

Dataset: The Pile

Neuron 4553 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: 1.6061. Min Range: -1.6061

Max Act: 1.6061. Min Act: -0.0000

Data Index: 1880779 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.3811. Min Act: -0.0000

Data Index: 1022161 (The Pile)

Max Activating Token Index: 685

Text #2

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5248. Min Act: -0.0000

Data Index: 1894127 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5107. Min Act: -0.0000

Data Index: 482904 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5199. Min Act: -0.0000

Data Index: 1570166 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.4327. Min Act: -0.0000

Data Index: 224436 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1255261 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.3794. Min Act: -0.0000

Data Index: 940145 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.3706. Min Act: -0.0000

Data Index: 907676 (The Pile)

Max Activating Token Index: 700

Text #9

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.4384. Min Act: -0.0000

Data Index: 1381472 (The Pile)

Max Activating Token Index: 642

Text #10

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.3855. Min Act: -0.0000

Data Index: 391665 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5198. Min Act: -0.0000

Data Index: 1970889 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.3728. Min Act: -0.0000

Data Index: 389067 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5020. Min Act: -0.0000

Data Index: 1340736 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.3668. Min Act: -0.0000

Data Index: 1434759 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.3023. Min Act: -0.0000

Data Index: 867769 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.4616. Min Act: -0.0000

Data Index: 1602798 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.3732. Min Act: -0.0000

Data Index: 764575 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.3074. Min Act: -0.0000

Data Index: 1798906 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.2819. Min Act: -0.0000

Data Index: 1647390 (The Pile)

Max Activating Token Index: 775