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

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

Neuron 3926 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4610. Min Range: -2.4610

Max Act: 2.4610. Min Act: -0.0000

Data Index: 1001561 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 2.4610. Min Range: -2.4610

Max Act: 2.2978. Min Act: -0.0000

Data Index: 372371 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 2.4610. Min Range: -2.4610

Max Act: 2.1106. Min Act: -0.0000

Data Index: 812329 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 2.4610. Min Range: -2.4610

Max Act: 2.0395. Min Act: -0.0000

Data Index: 882863 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 2.4610. Min Range: -2.4610

Max Act: 2.0333. Min Act: -0.0000

Data Index: 790503 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 2.4610. Min Range: -2.4610

Max Act: 2.1615. Min Act: -0.0000

Data Index: 420176 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 2.4610. Min Range: -2.4610

Max Act: 2.0077. Min Act: -0.0000

Data Index: 1161943 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 2.4610. Min Range: -2.4610

Max Act: 1.9975. Min Act: -0.0000

Data Index: 280268 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 2.4610. Min Range: -2.4610

Max Act: 2.2113. Min Act: -0.0000

Data Index: 1328344 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 2.4610. Min Range: -2.4610

Max Act: 2.0675. Min Act: -0.0000

Data Index: 1020848 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 2.4610. Min Range: -2.4610

Max Act: 1.8429. Min Act: -0.0000

Data Index: 1322918 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 2.4610. Min Range: -2.4610

Max Act: 1.9525. Min Act: -0.0000

Data Index: 297142 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 2.4610. Min Range: -2.4610

Max Act: 2.0310. Min Act: -0.0000

Data Index: 1246024 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 2.4610. Min Range: -2.4610

Max Act: 1.9211. Min Act: -0.0000

Data Index: 1198513 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 2.4610. Min Range: -2.4610

Max Act: 2.0403. Min Act: -0.0000

Data Index: 601011 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 2.4610. Min Range: -2.4610

Max Act: 1.8761. Min Act: -0.0000

Data Index: 457489 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 2.4610. Min Range: -2.4610

Max Act: 1.7620. Min Act: -0.0000

Data Index: 1193485 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 2.4610. Min Range: -2.4610

Max Act: 1.9656. Min Act: -0.0000

Data Index: 27137 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 2.4610. Min Range: -2.4610

Max Act: 1.8436. Min Act: -0.0000

Data Index: 561711 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 2.4610. Min Range: -2.4610

Max Act: 1.8556. Min Act: -0.0000

Data Index: 216121 (C4 (Web Text))

Max Activating Token Index: 592