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

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

Neuron 5000 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1890. Min Act: -0.0000

Data Index: 646143 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1542. Min Act: -0.0000

Data Index: 627422 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1613. Min Act: -0.0000

Data Index: 788554 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1574. Min Act: -0.0000

Data Index: 522087 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1501. Min Act: -0.0000

Data Index: 830045 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1539. Min Act: -0.0000

Data Index: 978808 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1664. Min Act: -0.0000

Data Index: 388766 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1481. Min Act: -0.0000

Data Index: 487429 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1518. Min Act: -0.0000

Data Index: 559501 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1214589 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1489. Min Act: -0.0000

Data Index: 269685 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1475. Min Act: -0.0000

Data Index: 993306 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1538. Min Act: -0.0000

Data Index: 446229 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1438. Min Act: -0.0000

Data Index: 577987 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1071853 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1061754 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1424. Min Act: -0.0000

Data Index: 902651 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1243204 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1416. Min Act: -0.0000

Data Index: 607183 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1416. Min Act: -0.0000

Data Index: 658829 (C4 (Web Text))

Max Activating Token Index: 730