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

Dataset: The Pile

Neuron 2070 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: 0.2269. Min Range: -0.2269

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1387337 (The Pile)

Max Activating Token Index: 239

Text #1

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.2269. Min Act: -0.0000

Data Index: 576027 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1446065 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.2098. Min Act: -0.0000

Data Index: 315107 (The Pile)

Max Activating Token Index: 695

Text #4

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1093776 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1745224 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1924322 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1048549 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1817. Min Act: -0.0000

Data Index: 253027 (The Pile)

Max Activating Token Index: 844

Text #9

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1036523 (The Pile)

Max Activating Token Index: 754

Text #10

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1839. Min Act: -0.0000

Data Index: 637536 (The Pile)

Max Activating Token Index: 325

Text #11

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1762. Min Act: -0.0000

Data Index: 218387 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1833. Min Act: -0.0000

Data Index: 41863 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1043604 (The Pile)

Max Activating Token Index: 719

Text #14

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1690. Min Act: -0.0000

Data Index: 943477 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1058660 (The Pile)

Max Activating Token Index: 289

Text #16

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1255487 (The Pile)

Max Activating Token Index: 206

Text #17

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1331031 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1588. Min Act: -0.0000

Data Index: 523416 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1245234 (The Pile)

Max Activating Token Index: 224