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

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

Neuron 2931 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2745. Min Act: -0.0000

Data Index: 938172 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1959. Min Act: -0.0000

Data Index: 370541 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1951. Min Act: -0.0000

Data Index: 661367 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1353616 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1872. Min Act: -0.0000

Data Index: 654617 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1779. Min Act: -0.0000

Data Index: 935121 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1647. Min Act: -0.0000

Data Index: 633189 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1614. Min Act: -0.0000

Data Index: 894748 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1507. Min Act: -0.0000

Data Index: 51301 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1593. Min Act: -0.0000

Data Index: 163103 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1502. Min Act: -0.0000

Data Index: 131441 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1562650 (Python Code)

Max Activating Token Index: 839

Text #12

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1586. Min Act: -0.0000

Data Index: 783155 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1157000 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1484610 (Python Code)

Max Activating Token Index: 761

Text #15

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1458. Min Act: -0.0000

Data Index: 1011950 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1526. Min Act: -0.0000

Data Index: 238447 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1222127 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1291154 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1468. Min Act: -0.0000

Data Index: 325519 (C4 (Web Text))

Max Activating Token Index: 360