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

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

Neuron 2325 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.2149. Min Act: -0.0001

Data Index: 223172 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1954. Min Act: -0.0000

Data Index: 867218 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1765. Min Act: -0.0000

Data Index: 419572 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1919. Min Act: -0.0000

Data Index: 373590 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1709. Min Act: -0.0001

Data Index: 968739 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1716. Min Act: -0.0001

Data Index: 514607 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1573. Min Act: -0.0000

Data Index: 349280 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1604. Min Act: -0.0001

Data Index: 697121 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1710. Min Act: -0.0001

Data Index: 738418 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1585. Min Act: -0.0000

Data Index: 644577 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1413. Min Act: -0.0001

Data Index: 686805 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1327005 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1686. Min Act: -0.0001

Data Index: 369839 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1496. Min Act: -0.0000

Data Index: 916819 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1416. Min Act: -0.0000

Data Index: 654616 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1533. Min Act: -0.0001

Data Index: 81469 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1595. Min Act: -0.0001

Data Index: 8097 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1544. Min Act: -0.0001

Data Index: 933886 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1491. Min Act: -0.0001

Data Index: 508614 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.2149. Min Range: -0.2149

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1284506 (C4 (Web Text))

Max Activating Token Index: 774