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

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

Neuron 4925 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1934. Min Act: -0.0002

Data Index: 1192349 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1926. Min Act: -0.0002

Data Index: 24835 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1888. Min Act: -0.0002

Data Index: 962340 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1886. Min Act: -0.0002

Data Index: 367550 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1770. Min Act: -0.0002

Data Index: 1124963 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1751. Min Act: -0.0002

Data Index: 962796 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1759. Min Act: -0.0002

Data Index: 1292475 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1734. Min Act: -0.0002

Data Index: 617995 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1687. Min Act: -0.0002

Data Index: 1084153 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1620. Min Act: -0.0002

Data Index: 595967 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1705. Min Act: -0.0002

Data Index: 814835 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1650. Min Act: -0.0002

Data Index: 309674 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1619. Min Act: -0.0002

Data Index: 1042711 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1646. Min Act: -0.0003

Data Index: 947713 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1616. Min Act: -0.0002

Data Index: 33137 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1592. Min Act: -0.0002

Data Index: 2050 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1570. Min Act: -0.0002

Data Index: 71654 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1539. Min Act: -0.0002

Data Index: 131001 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1486. Min Act: -0.0002

Data Index: 1066156 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1491. Min Act: -0.0002

Data Index: 225981 (C4 (Web Text))

Max Activating Token Index: 702