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

Dataset: The Pile

Neuron 1542 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1170. Min Range: -8.1170

Max Act: 8.1170. Min Act: -0.0000

Data Index: 1875931 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 8.1170. Min Range: -8.1170

Max Act: 7.4519. Min Act: -0.0000

Data Index: 1116954 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 8.1170. Min Range: -8.1170

Max Act: 7.0797. Min Act: -0.0000

Data Index: 1552592 (The Pile)

Max Activating Token Index: 936

Text #3

Max Range: 8.1170. Min Range: -8.1170

Max Act: 7.6025. Min Act: -0.0000

Data Index: 337663 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.8035. Min Act: -0.0000

Data Index: 1770787 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.5202. Min Act: -0.0000

Data Index: 593796 (The Pile)

Max Activating Token Index: 129

Text #6

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.4894. Min Act: -0.0000

Data Index: 1793568 (The Pile)

Max Activating Token Index: 876

Text #7

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.8607. Min Act: -0.0000

Data Index: 415366 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.3049. Min Act: -0.0000

Data Index: 1143465 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.0854. Min Act: -0.0000

Data Index: 1920275 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.3763. Min Act: -0.0000

Data Index: 1461862 (The Pile)

Max Activating Token Index: 1018

Text #11

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.3031. Min Act: -0.0000

Data Index: 508609 (The Pile)

Max Activating Token Index: 747

Text #12

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.5826. Min Act: -0.0000

Data Index: 313148 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.3453. Min Act: -0.0000

Data Index: 1502124 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.5201. Min Act: -0.0000

Data Index: 629454 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 8.1170. Min Range: -8.1170

Max Act: 5.4154. Min Act: -0.0000

Data Index: 1228468 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.6824. Min Act: -0.0000

Data Index: 879624 (The Pile)

Max Activating Token Index: 289

Text #17

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.7647. Min Act: -0.0000

Data Index: 1468119 (The Pile)

Max Activating Token Index: 1017

Text #18

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.1572. Min Act: -0.0000

Data Index: 118045 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 8.1170. Min Range: -8.1170

Max Act: 6.0621. Min Act: -0.0000

Data Index: 1408421 (The Pile)

Max Activating Token Index: 350