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

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

Neuron 2773 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0950. Min Act: -0.0001

Data Index: 307285 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.1662. Min Act: -0.0001

Data Index: 692452 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0539. Min Act: -0.0001

Data Index: 59514 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9845. Min Act: -0.0001

Data Index: 423954 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9229. Min Act: -0.0001

Data Index: 612678 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9679. Min Act: -0.0001

Data Index: 840216 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9332. Min Act: -0.0001

Data Index: 1409043 (Python Code)

Max Activating Token Index: 328

Text #7

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9419. Min Act: -0.0001

Data Index: 1224323 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8737. Min Act: -0.0001

Data Index: 791390 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8717. Min Act: -0.0001

Data Index: 1610189 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8955. Min Act: -0.0001

Data Index: 937212 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9165. Min Act: -0.0001

Data Index: 8807 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8946. Min Act: -0.0001

Data Index: 1063684 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8977. Min Act: -0.0001

Data Index: 628118 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8940. Min Act: -0.0001

Data Index: 493542 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8855. Min Act: -0.0001

Data Index: 127483 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8864. Min Act: -0.0001

Data Index: 475533 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8950. Min Act: -0.0001

Data Index: 52485 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9347. Min Act: -0.0001

Data Index: 1440275 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8838. Min Act: -0.0001

Data Index: 1192971 (C4 (Web Text))

Max Activating Token Index: 138