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

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

Neuron 5416 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: 0.1773. Min Range: -0.1773

Max Act: 0.1738. Min Act: -0.0000

Data Index: 47972 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1752. Min Act: -0.0000

Data Index: 253896 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1599. Min Act: -0.0000

Data Index: 778303 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1108110 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1225512 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1450756 (Python Code)

Max Activating Token Index: 648

Text #6

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1627. Min Act: -0.0000

Data Index: 736615 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1433. Min Act: -0.0000

Data Index: 27284 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1683. Min Act: -0.0000

Data Index: 554189 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1693. Min Act: -0.0000

Data Index: 678986 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1475. Min Act: -0.0000

Data Index: 457028 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1580. Min Act: -0.0000

Data Index: 664560 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1492. Min Act: -0.0000

Data Index: 747708 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1517. Min Act: -0.0000

Data Index: 481187 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1453. Min Act: -0.0000

Data Index: 954850 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1488. Min Act: -0.0000

Data Index: 255163 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1419. Min Act: -0.0000

Data Index: 821067 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1084668 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1460. Min Act: -0.0000

Data Index: 802540 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1460. Min Act: -0.0000

Data Index: 204827 (C4 (Web Text))

Max Activating Token Index: 891