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

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

Neuron 719 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1455427 (Python Code)

Max Activating Token Index: 1005

Text #1

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1302367 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1451543 (Python Code)

Max Activating Token Index: 370

Text #3

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1621692 (Python Code)

Max Activating Token Index: 260

Text #4

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1449214 (Python Code)

Max Activating Token Index: 847

Text #5

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2313. Min Act: -0.0000

Data Index: 645420 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1604159 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1255501 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2177. Min Act: -0.0000

Data Index: 660741 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1561199 (Python Code)

Max Activating Token Index: 316

Text #10

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1578624 (Python Code)

Max Activating Token Index: 717

Text #11

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1621999 (Python Code)

Max Activating Token Index: 903

Text #12

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.1907. Min Act: -0.0000

Data Index: 603170 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1009728 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.1825. Min Act: -0.0000

Data Index: 540852 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1180065 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.1723. Min Act: -0.0000

Data Index: 725318 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1612585 (Python Code)

Max Activating Token Index: 353

Text #18

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1352631 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.1657. Min Act: -0.0000

Data Index: 877131 (C4 (Web Text))

Max Activating Token Index: 819