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

Dataset: The Pile

Neuron 3731 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: 0.1695. Min Range: -0.1695

Max Act: 0.1695. Min Act: -0.0000

Data Index: 389930 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1565722 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1687840 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1191. Min Act: -0.0000

Data Index: 896143 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1256. Min Act: -0.0000

Data Index: 183658 (The Pile)

Max Activating Token Index: 234

Text #5

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1045920 (The Pile)

Max Activating Token Index: 732

Text #6

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1052. Min Act: -0.0000

Data Index: 177677 (The Pile)

Max Activating Token Index: 997

Text #7

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1022. Min Act: -0.0000

Data Index: 77629 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1199630 (The Pile)

Max Activating Token Index: 963

Text #9

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1720057 (The Pile)

Max Activating Token Index: 635

Text #10

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1963984 (The Pile)

Max Activating Token Index: 532

Text #11

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1321566 (The Pile)

Max Activating Token Index: 741

Text #12

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1778606 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.0959. Min Act: -0.0000

Data Index: 771738 (The Pile)

Max Activating Token Index: 865

Text #14

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1655168 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1046. Min Act: -0.0000

Data Index: 874944 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.0984. Min Act: -0.0000

Data Index: 293202 (The Pile)

Max Activating Token Index: 435

Text #17

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.0968. Min Act: -0.0000

Data Index: 894905 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1021. Min Act: -0.0000

Data Index: 373214 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1006. Min Act: -0.0000

Data Index: 752862 (The Pile)

Max Activating Token Index: 547