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

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

Neuron 2302 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1389047 (Python Code)

Max Activating Token Index: 467

Text #1

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1442438 (Python Code)

Max Activating Token Index: 281

Text #2

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0763. Min Act: -0.0000

Data Index: 1498399 (Python Code)

Max Activating Token Index: 322

Text #3

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1438745 (Python Code)

Max Activating Token Index: 655

Text #4

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1582527 (Python Code)

Max Activating Token Index: 298

Text #5

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1597519 (Python Code)

Max Activating Token Index: 805

Text #6

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0710. Min Act: -0.0001

Data Index: 321782 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1389811 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1486430 (Python Code)

Max Activating Token Index: 445

Text #9

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1393001 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1618687 (Python Code)

Max Activating Token Index: 481

Text #11

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1484722 (Python Code)

Max Activating Token Index: 351

Text #12

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1397175 (Python Code)

Max Activating Token Index: 304

Text #13

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1467277 (Python Code)

Max Activating Token Index: 641

Text #14

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1367804 (Python Code)

Max Activating Token Index: 587

Text #15

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1578617 (Python Code)

Max Activating Token Index: 337

Text #16

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1529836 (Python Code)

Max Activating Token Index: 620

Text #17

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0698. Min Act: -0.0001

Data Index: 650787 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1513080 (Python Code)

Max Activating Token Index: 602

Text #19

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1524162 (Python Code)

Max Activating Token Index: 880