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

Dataset: The Pile

Neuron 3042 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: 0.2942. Min Range: -0.2942

Max Act: 0.2942. Min Act: -0.0000

Data Index: 136240 (The Pile)

Max Activating Token Index: 762

Text #1

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2012. Min Act: -0.0000

Data Index: 544308 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2069. Min Act: -0.0000

Data Index: 89035 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1313055 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1807. Min Act: -0.0000

Data Index: 774969 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1735. Min Act: -0.0000

Data Index: 692261 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1830. Min Act: -0.0000

Data Index: 587565 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1767. Min Act: -0.0000

Data Index: 700484 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1792. Min Act: -0.0000

Data Index: 708934 (The Pile)

Max Activating Token Index: 296

Text #9

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1575093 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1381453 (The Pile)

Max Activating Token Index: 325

Text #11

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1670495 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1689730 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1722. Min Act: -0.0000

Data Index: 906711 (The Pile)

Max Activating Token Index: 688

Text #14

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1132064 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1849713 (The Pile)

Max Activating Token Index: 553

Text #16

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1136476 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1705. Min Act: -0.0000

Data Index: 972220 (The Pile)

Max Activating Token Index: 589

Text #18

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1283759 (The Pile)

Max Activating Token Index: 569

Text #19

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1717939 (The Pile)

Max Activating Token Index: 973