Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2879 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2490. Min Act: -0.0000

Data Index: 841202 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1467461 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2085. Min Act: -0.0000

Data Index: 745582 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1856. Min Act: -0.0000

Data Index: 158836 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1926. Min Act: -0.0000

Data Index: 497041 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1982313 (The Pile)

Max Activating Token Index: 582

Text #6

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1727. Min Act: -0.0000

Data Index: 543165 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1651957 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1694. Min Act: -0.0000

Data Index: 53961 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1652. Min Act: -0.0000

Data Index: 1123009 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1757. Min Act: -0.0000

Data Index: 66673 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1208342 (The Pile)

Max Activating Token Index: 488

Text #12

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1844131 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1906873 (The Pile)

Max Activating Token Index: 466

Text #14

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1570. Min Act: -0.0000

Data Index: 942829 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1586. Min Act: -0.0000

Data Index: 514143 (The Pile)

Max Activating Token Index: 951

Text #16

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1585. Min Act: -0.0000

Data Index: 73183 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1509522 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1537. Min Act: -0.0000

Data Index: 283108 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1943005 (The Pile)

Max Activating Token Index: 779