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

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

Neuron 3642 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9922. Min Range: -1.9922

Max Act: 1.9922. Min Act: -0.0000

Data Index: 808892 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.9922. Min Range: -1.9922

Max Act: 1.8488. Min Act: -0.0000

Data Index: 1218094 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 1.9922. Min Range: -1.9922

Max Act: 1.8846. Min Act: -0.0000

Data Index: 198258 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.9757. Min Act: -0.0000

Data Index: 29160 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.8669. Min Act: -0.0000

Data Index: 676788 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.8297. Min Act: -0.0000

Data Index: 569975 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1060872 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.7717. Min Act: -0.0000

Data Index: 55917 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.8199. Min Act: 0.0000

Data Index: 943532 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.7762. Min Act: -0.0000

Data Index: 333022 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.7612. Min Act: -0.0000

Data Index: 519178 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1112454 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1337970 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.7017. Min Act: -0.0000

Data Index: 803438 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.6890. Min Act: -0.0000

Data Index: 427234 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.6582. Min Act: -0.0000

Data Index: 265458 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.6488. Min Act: -0.0000

Data Index: 235961 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.6390. Min Act: -0.0000

Data Index: 368472 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.6566. Min Act: -0.0000

Data Index: 402141 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 1.9922. Min Range: -1.9922

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1209910 (C4 (Web Text))

Max Activating Token Index: 428