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

Dataset: The Pile

Neuron 501 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: 0.9697. Min Range: -0.9697

Max Act: 0.9293. Min Act: -0.0000

Data Index: 1554584 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1724182 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1596653 (The Pile)

Max Activating Token Index: 796

Text #3

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1493484 (The Pile)

Max Activating Token Index: 761

Text #4

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1608823 (The Pile)

Max Activating Token Index: 906

Text #5

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1182487 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1236008 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7979. Min Act: -0.0000

Data Index: 349547 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7851. Min Act: -0.0000

Data Index: 889889 (The Pile)

Max Activating Token Index: 1012

Text #9

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1606225 (The Pile)

Max Activating Token Index: 705

Text #10

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7690. Min Act: -0.0000

Data Index: 257001 (The Pile)

Max Activating Token Index: 297

Text #11

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7840. Min Act: -0.0000

Data Index: 786082 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1966568 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1079865 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1716009 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8174. Min Act: -0.0000

Data Index: 744938 (The Pile)

Max Activating Token Index: 942

Text #16

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8080. Min Act: -0.0000

Data Index: 210884 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1212832 (The Pile)

Max Activating Token Index: 476

Text #18

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1347367 (The Pile)

Max Activating Token Index: 312

Text #19

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7868. Min Act: -0.0000

Data Index: 843733 (The Pile)

Max Activating Token Index: 254