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

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

Neuron 1458 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1834. Min Act: -0.0001

Data Index: 1172242 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1844. Min Act: -0.0001

Data Index: 65722 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1649. Min Act: -0.0001

Data Index: 882008 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1835. Min Act: -0.0001

Data Index: 496399 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1854. Min Act: -0.0001

Data Index: 449896 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1700. Min Act: -0.0001

Data Index: 1053554 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1599. Min Act: -0.0001

Data Index: 931920 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1546. Min Act: -0.0001

Data Index: 1182686 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1625. Min Act: -0.0001

Data Index: 776880 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1563. Min Act: -0.0001

Data Index: 880012 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1099801 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1656. Min Act: -0.0001

Data Index: 135340 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1417. Min Act: -0.0001

Data Index: 929648 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1700. Min Act: -0.0001

Data Index: 73263 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1040017 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1565. Min Act: -0.0001

Data Index: 465780 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1595. Min Act: -0.0001

Data Index: 746503 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1653. Min Act: -0.0001

Data Index: 84647 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1531. Min Act: -0.0001

Data Index: 1041020 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1458. Min Act: -0.0001

Data Index: 523647 (C4 (Web Text))

Max Activating Token Index: 45