Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3006 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.5532. Min Act: -0.0001

Data Index: 350769 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.3699. Min Act: -0.0001

Data Index: 933846 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.3252. Min Act: -0.0001

Data Index: 636511 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.3259. Min Act: -0.0001

Data Index: 91368 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.3496. Min Act: -0.0001

Data Index: 209524 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.2767. Min Act: -0.0001

Data Index: 826155 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.2685. Min Act: -0.0001

Data Index: 261409 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.1651. Min Act: -0.0001

Data Index: 883641 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.2082. Min Act: -0.0001

Data Index: 419514 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.0674. Min Act: -0.0001

Data Index: 205571 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.2179. Min Act: -0.0001

Data Index: 35290 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.0898. Min Act: -0.0001

Data Index: 849524 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.1217. Min Act: -0.0001

Data Index: 1253963 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.1886. Min Act: -0.0001

Data Index: 1139125 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.1804. Min Act: -0.0001

Data Index: 93543 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.2132. Min Act: -0.0001

Data Index: 836478 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.2429. Min Act: -0.0001

Data Index: 508707 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.2022. Min Act: -0.0001

Data Index: 602292 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.2364. Min Act: -0.0001

Data Index: 1312211 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 1.5532. Min Range: -1.5532

Max Act: 1.1398. Min Act: -0.0001

Data Index: 711983 (C4 (Web Text))

Max Activating Token Index: 351