Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4443 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.7453. Min Range: -6.7453

Max Act: 6.7453. Min Act: -0.0000

Data Index: 637723 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 6.7453. Min Range: -6.7453

Max Act: 6.4587. Min Act: -0.0000

Data Index: 224718 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 6.7453. Min Range: -6.7453

Max Act: 6.3277. Min Act: -0.0000

Data Index: 1309368 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 6.7453. Min Range: -6.7453

Max Act: 6.1617. Min Act: -0.0000

Data Index: 907151 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 6.7453. Min Range: -6.7453

Max Act: 6.3364. Min Act: -0.0000

Data Index: 63177 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 6.7453. Min Range: -6.7453

Max Act: 6.0724. Min Act: -0.0000

Data Index: 637980 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 6.7453. Min Range: -6.7453

Max Act: 6.0431. Min Act: -0.0000

Data Index: 1353390 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.6231. Min Act: -0.0000

Data Index: 431642 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.9617. Min Act: -0.0000

Data Index: 1061651 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.7126. Min Act: -0.0000

Data Index: 1204121 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.7205. Min Act: -0.0000

Data Index: 468565 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.6278. Min Act: -0.0000

Data Index: 544325 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.6157. Min Act: -0.0000

Data Index: 595436 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.6071. Min Act: -0.0000

Data Index: 864355 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.5894. Min Act: -0.0000

Data Index: 866844 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.6783. Min Act: -0.0000

Data Index: 390748 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.4620. Min Act: -0.0000

Data Index: 429013 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.2054. Min Act: -0.0000

Data Index: 1046731 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.5335. Min Act: -0.0000

Data Index: 1311083 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 6.7453. Min Range: -6.7453

Max Act: 5.2989. Min Act: -0.0000

Data Index: 573035 (C4 (Web Text))

Max Activating Token Index: 929