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

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

Neuron 2689 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3582. Min Range: -2.3582

Max Act: 2.3582. Min Act: -0.0000

Data Index: 357310 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 2.3582. Min Range: -2.3582

Max Act: 2.2233. Min Act: -0.0000

Data Index: 309330 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 2.3582. Min Range: -2.3582

Max Act: 2.1814. Min Act: -0.0000

Data Index: 385652 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 2.3582. Min Range: -2.3582

Max Act: 2.1474. Min Act: -0.0000

Data Index: 1130201 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 2.3582. Min Range: -2.3582

Max Act: 2.2056. Min Act: -0.0000

Data Index: 76439 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 2.3582. Min Range: -2.3582

Max Act: 2.0794. Min Act: -0.0000

Data Index: 1009896 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 2.3582. Min Range: -2.3582

Max Act: 1.9802. Min Act: -0.0000

Data Index: 290759 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 2.3582. Min Range: -2.3582

Max Act: 2.0777. Min Act: -0.0000

Data Index: 352179 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 2.3582. Min Range: -2.3582

Max Act: 2.0116. Min Act: -0.0000

Data Index: 159637 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 2.3582. Min Range: -2.3582

Max Act: 2.1187. Min Act: -0.0000

Data Index: 1163818 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 2.3582. Min Range: -2.3582

Max Act: 2.1147. Min Act: -0.0000

Data Index: 309069 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 2.3582. Min Range: -2.3582

Max Act: 1.9938. Min Act: -0.0000

Data Index: 1120068 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 2.3582. Min Range: -2.3582

Max Act: 1.9889. Min Act: -0.0000

Data Index: 446849 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 2.3582. Min Range: -2.3582

Max Act: 1.9861. Min Act: -0.0000

Data Index: 1243839 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 2.3582. Min Range: -2.3582

Max Act: 1.8561. Min Act: -0.0000

Data Index: 47894 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 2.3582. Min Range: -2.3582

Max Act: 1.8606. Min Act: -0.0000

Data Index: 123867 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 2.3582. Min Range: -2.3582

Max Act: 1.9642. Min Act: -0.0000

Data Index: 838822 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 2.3582. Min Range: -2.3582

Max Act: 1.8531. Min Act: -0.0000

Data Index: 566383 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 2.3582. Min Range: -2.3582

Max Act: 1.9040. Min Act: -0.0000

Data Index: 790390 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 2.3582. Min Range: -2.3582

Max Act: 1.9035. Min Act: -0.0000

Data Index: 838319 (C4 (Web Text))

Max Activating Token Index: 543