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

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

Neuron 1586 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2127. Min Range: -1.2127

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1355805 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8771. Min Act: -0.0000

Data Index: 657923 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8714. Min Act: -0.0000

Data Index: 648948 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8185. Min Act: -0.0000

Data Index: 882789 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.9553. Min Act: -0.0000

Data Index: 795724 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1321162 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1044875 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8104. Min Act: -0.0000

Data Index: 750326 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.7943. Min Act: -0.0000

Data Index: 708316 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8578. Min Act: -0.0000

Data Index: 442717 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8730. Min Act: -0.0000

Data Index: 189284 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8086. Min Act: -0.0000

Data Index: 318731 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8900. Min Act: -0.0000

Data Index: 819343 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8680. Min Act: -0.0000

Data Index: 857819 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.9071. Min Act: -0.0000

Data Index: 342851 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1296350 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8140. Min Act: -0.0000

Data Index: 527424 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.8000. Min Act: -0.0000

Data Index: 878515 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.7893. Min Act: -0.0000

Data Index: 996943 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 1.2127. Min Range: -1.2127

Max Act: 0.7984. Min Act: -0.0000

Data Index: 304418 (C4 (Web Text))

Max Activating Token Index: 838