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

Dataset: The Pile

Neuron 4132 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: 0.2586. Min Range: -0.2586

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1309948 (The Pile)

Max Activating Token Index: 7

Text #1

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1412596 (The Pile)

Max Activating Token Index: 28

Text #2

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2357. Min Act: -0.0000

Data Index: 633008 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2388. Min Act: -0.0000

Data Index: 358134 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2049. Min Act: -0.0000

Data Index: 22117 (The Pile)

Max Activating Token Index: 592

Text #5

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1534460 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1863. Min Act: -0.0000

Data Index: 712602 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1294794 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1718008 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1174937 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2017. Min Act: -0.0000

Data Index: 374358 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1940926 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1451619 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1843. Min Act: -0.0000

Data Index: 806155 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1900. Min Act: -0.0000

Data Index: 257560 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1814. Min Act: -0.0000

Data Index: 479081 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1851. Min Act: -0.0000

Data Index: 370771 (The Pile)

Max Activating Token Index: 276

Text #17

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1368184 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1841. Min Act: -0.0000

Data Index: 137719 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1787. Min Act: -0.0000

Data Index: 792834 (The Pile)

Max Activating Token Index: 208