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

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

Neuron 2952 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7824. Min Range: -2.7824

Max Act: 2.7824. Min Act: -0.0001

Data Index: 194357 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 2.7824. Min Range: -2.7824

Max Act: 2.4627. Min Act: -0.0001

Data Index: 549225 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 2.7824. Min Range: -2.7824

Max Act: 2.6009. Min Act: -0.0000

Data Index: 1218738 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 2.7824. Min Range: -2.7824

Max Act: 2.4237. Min Act: -0.0001

Data Index: 749325 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 2.7824. Min Range: -2.7824

Max Act: 2.5427. Min Act: -0.0000

Data Index: 685563 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 2.7824. Min Range: -2.7824

Max Act: 2.5408. Min Act: -0.0001

Data Index: 999943 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 2.7824. Min Range: -2.7824

Max Act: 2.1753. Min Act: -0.0000

Data Index: 571879 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 2.7824. Min Range: -2.7824

Max Act: 2.2789. Min Act: -0.0001

Data Index: 400552 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 2.7824. Min Range: -2.7824

Max Act: 2.1325. Min Act: -0.0000

Data Index: 437361 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 2.7824. Min Range: -2.7824

Max Act: 2.1419. Min Act: -0.0000

Data Index: 274594 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 2.7824. Min Range: -2.7824

Max Act: 1.9636. Min Act: -0.0000

Data Index: 1092330 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 2.7824. Min Range: -2.7824

Max Act: 1.8889. Min Act: -0.0000

Data Index: 970163 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 2.7824. Min Range: -2.7824

Max Act: 1.9563. Min Act: -0.0000

Data Index: 464188 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 2.7824. Min Range: -2.7824

Max Act: 1.9526. Min Act: -0.0000

Data Index: 794554 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 2.7824. Min Range: -2.7824

Max Act: 1.9024. Min Act: -0.0000

Data Index: 126339 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 2.7824. Min Range: -2.7824

Max Act: 1.8110. Min Act: -0.0000

Data Index: 905029 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 2.7824. Min Range: -2.7824

Max Act: 1.8123. Min Act: -0.0000

Data Index: 799189 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 2.7824. Min Range: -2.7824

Max Act: 1.7886. Min Act: -0.0000

Data Index: 777436 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 2.7824. Min Range: -2.7824

Max Act: 1.8028. Min Act: -0.0000

Data Index: 1356414 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 2.7824. Min Range: -2.7824

Max Act: 1.6078. Min Act: -0.0000

Data Index: 50373 (C4 (Web Text))

Max Activating Token Index: 512