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

Dataset: The Pile

Neuron 4100 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0611. Min Range: -1.0611

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1459374 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9782. Min Act: -0.0000

Data Index: 665620 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8863. Min Act: -0.0000

Data Index: 607051 (The Pile)

Max Activating Token Index: 93

Text #3

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7956. Min Act: -0.0000

Data Index: 969031 (The Pile)

Max Activating Token Index: 736

Text #4

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1852015 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8116. Min Act: -0.0000

Data Index: 484664 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1876042 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1297887 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7429. Min Act: -0.0000

Data Index: 141885 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7619. Min Act: -0.0000

Data Index: 647715 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7592. Min Act: -0.0000

Data Index: 34815 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1665245 (The Pile)

Max Activating Token Index: 355

Text #12

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1432170 (The Pile)

Max Activating Token Index: 828

Text #13

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.6991. Min Act: -0.0000

Data Index: 79014 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1390117 (The Pile)

Max Activating Token Index: 859

Text #15

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7377. Min Act: -0.0000

Data Index: 26451 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1720047 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7053. Min Act: -0.0000

Data Index: 552272 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1748708 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1728176 (The Pile)

Max Activating Token Index: 540