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

Dataset: The Pile

Neuron 1343 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: 0.2396. Min Range: -0.2396

Max Act: 0.2396. Min Act: -0.0000

Data Index: 830750 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1073781 (The Pile)

Max Activating Token Index: 969

Text #2

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1214671 (The Pile)

Max Activating Token Index: 837

Text #3

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1457627 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1730. Min Act: -0.0000

Data Index: 492811 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1161693 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2120. Min Act: -0.0000

Data Index: 121135 (The Pile)

Max Activating Token Index: 921

Text #7

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1951. Min Act: -0.0000

Data Index: 422000 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2007. Min Act: -0.0000

Data Index: 7999 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1397513 (The Pile)

Max Activating Token Index: 882

Text #10

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1385978 (The Pile)

Max Activating Token Index: 674

Text #11

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1837. Min Act: -0.0000

Data Index: 140362 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1946. Min Act: -0.0000

Data Index: 636093 (The Pile)

Max Activating Token Index: 986

Text #13

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1908. Min Act: -0.0000

Data Index: 447478 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1292181 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1564. Min Act: -0.0000

Data Index: 91927 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1873. Min Act: -0.0000

Data Index: 642957 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1825538 (The Pile)

Max Activating Token Index: 783

Text #18

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1919. Min Act: -0.0000

Data Index: 268055 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1678. Min Act: -0.0000

Data Index: 486162 (The Pile)

Max Activating Token Index: 696