Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 559 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.2753. Min Act: -0.0001

Data Index: 1331829 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.2615. Min Act: -0.0001

Data Index: 261456 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.2478. Min Act: -0.0001

Data Index: 482860 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.2262. Min Act: -0.0001

Data Index: 148160 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.2300. Min Act: -0.0000

Data Index: 75451 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.2030. Min Act: -0.0001

Data Index: 319114 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.2054. Min Act: -0.0001

Data Index: 601380 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.2160. Min Act: -0.0001

Data Index: 366876 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.1860. Min Act: -0.0000

Data Index: 252798 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.2119. Min Act: -0.0001

Data Index: 339541 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.1738. Min Act: -0.0001

Data Index: 1623937 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.1405. Min Act: -0.0001

Data Index: 648676 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.1879. Min Act: -0.0001

Data Index: 350821 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1533801 (Python Code)

Max Activating Token Index: 465

Text #14

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.1535. Min Act: -0.0001

Data Index: 104594 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.1632. Min Act: -0.0001

Data Index: 1461021 (Python Code)

Max Activating Token Index: 207

Text #16

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.1735. Min Act: -0.0000

Data Index: 535980 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1320690 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.1553. Min Act: -0.0001

Data Index: 301300 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.2753. Min Range: -0.2753

Max Act: 0.1583. Min Act: -0.0001

Data Index: 433217 (C4 (Web Text))

Max Activating Token Index: 103