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

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

Neuron 187 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2243. Min Act: -0.0000

Data Index: 873531 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1976. Min Act: -0.0001

Data Index: 646986 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2079. Min Act: -0.0000

Data Index: 920568 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2127. Min Act: -0.0001

Data Index: 444871 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2029. Min Act: -0.0000

Data Index: 394562 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2068. Min Act: -0.0000

Data Index: 298708 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2006. Min Act: -0.0001

Data Index: 184367 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2041. Min Act: -0.0000

Data Index: 183695 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.2004. Min Act: -0.0000

Data Index: 347922 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1808. Min Act: -0.0001

Data Index: 1003672 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1867. Min Act: -0.0000

Data Index: 595728 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1889. Min Act: -0.0001

Data Index: 763389 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1797. Min Act: -0.0001

Data Index: 1336984 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1920. Min Act: -0.0000

Data Index: 267270 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1706. Min Act: -0.0001

Data Index: 958464 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1643. Min Act: -0.0001

Data Index: 904431 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1391151 (Python Code)

Max Activating Token Index: 1016

Text #17

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1216760 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1040049 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.2243. Min Range: -0.2243

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1064440 (C4 (Web Text))

Max Activating Token Index: 557