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

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

Neuron 3867 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1590. Min Range: -3.1590

Max Act: 3.1590. Min Act: -0.0000

Data Index: 1263937 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 3.1590. Min Range: -3.1590

Max Act: 2.6083. Min Act: -0.0000

Data Index: 270708 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 3.1590. Min Range: -3.1590

Max Act: 2.6012. Min Act: -0.0000

Data Index: 1119906 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 3.1590. Min Range: -3.1590

Max Act: 2.3080. Min Act: -0.0000

Data Index: 1255161 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 3.1590. Min Range: -3.1590

Max Act: 2.2562. Min Act: -0.0000

Data Index: 678637 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 3.1590. Min Range: -3.1590

Max Act: 2.3655. Min Act: -0.0000

Data Index: 1226024 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 3.1590. Min Range: -3.1590

Max Act: 2.0843. Min Act: -0.0000

Data Index: 1246367 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 3.1590. Min Range: -3.1590

Max Act: 2.0094. Min Act: -0.0000

Data Index: 545625 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.9979. Min Act: -0.0000

Data Index: 150949 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.8833. Min Act: -0.0000

Data Index: 738221 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.8786. Min Act: -0.0000

Data Index: 1312970 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.9283. Min Act: -0.0000

Data Index: 1333068 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.9204. Min Act: -0.0000

Data Index: 826425 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.7605. Min Act: -0.0000

Data Index: 1298197 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.7468. Min Act: -0.0000

Data Index: 393858 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.8473. Min Act: -0.0000

Data Index: 682069 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.7373. Min Act: -0.0000

Data Index: 1228720 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.8360. Min Act: -0.0000

Data Index: 583615 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.7133. Min Act: -0.0000

Data Index: 927478 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 3.1590. Min Range: -3.1590

Max Act: 1.7771. Min Act: -0.0000

Data Index: 394836 (C4 (Web Text))

Max Activating Token Index: 871