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

Dataset: The Pile

Neuron 4770 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1151066 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2009. Min Act: -0.0000

Data Index: 37220 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2008. Min Act: -0.0000

Data Index: 548971 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1111731 (The Pile)

Max Activating Token Index: 978

Text #4

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1724. Min Act: -0.0000

Data Index: 4355 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1576. Min Act: -0.0000

Data Index: 342915 (The Pile)

Max Activating Token Index: 155

Text #6

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1764. Min Act: -0.0000

Data Index: 796566 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1650841 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1752000 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1744. Min Act: -0.0000

Data Index: 235896 (The Pile)

Max Activating Token Index: 651

Text #10

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1608. Min Act: -0.0000

Data Index: 625734 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1477052 (The Pile)

Max Activating Token Index: 660

Text #12

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1456242 (The Pile)

Max Activating Token Index: 987

Text #13

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1302547 (The Pile)

Max Activating Token Index: 405

Text #14

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1462. Min Act: -0.0000

Data Index: 445191 (The Pile)

Max Activating Token Index: 35

Text #15

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1503162 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1523655 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1719687 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1543338 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1790340 (The Pile)

Max Activating Token Index: 888