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

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

Neuron 3717 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2277. Min Act: -0.0001

Data Index: 1224388 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1042835 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1885. Min Act: -0.0000

Data Index: 167440 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1589966 (Python Code)

Max Activating Token Index: 415

Text #4

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1812. Min Act: -0.0000

Data Index: 329740 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1788. Min Act: -0.0000

Data Index: 348851 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1715. Min Act: -0.0000

Data Index: 506627 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1577. Min Act: -0.0001

Data Index: 1324668 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1531. Min Act: -0.0000

Data Index: 422015 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1548. Min Act: -0.0000

Data Index: 665574 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1606. Min Act: -0.0000

Data Index: 751629 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1341. Min Act: -0.0000

Data Index: 150696 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1535. Min Act: -0.0001

Data Index: 157361 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1336891 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1592. Min Act: -0.0000

Data Index: 637008 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1560588 (Python Code)

Max Activating Token Index: 428

Text #16

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1583. Min Act: -0.0000

Data Index: 936597 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1732. Min Act: -0.0001

Data Index: 697859 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1089966 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1407. Min Act: -0.0000

Data Index: 898993 (C4 (Web Text))

Max Activating Token Index: 341