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

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

Neuron 2823 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0768. Min Act: -0.0000

Data Index: 214150 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0727. Min Act: -0.0001

Data Index: 37940 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0694. Min Act: -0.0001

Data Index: 766804 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1338570 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0684. Min Act: -0.0001

Data Index: 860029 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1527268 (Python Code)

Max Activating Token Index: 573

Text #6

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1496580 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0640. Min Act: -0.0001

Data Index: 475910 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1532032 (Python Code)

Max Activating Token Index: 465

Text #9

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0621. Min Act: -0.0001

Data Index: 140494 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0624. Min Act: -0.0001

Data Index: 385391 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0669. Min Act: -0.0001

Data Index: 522383 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0631. Min Act: -0.0001

Data Index: 835075 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1393071 (Python Code)

Max Activating Token Index: 355

Text #14

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1487490 (Python Code)

Max Activating Token Index: 526

Text #15

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1592236 (Python Code)

Max Activating Token Index: 196

Text #16

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1365304 (Python Code)

Max Activating Token Index: 511

Text #17

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1500260 (Python Code)

Max Activating Token Index: 280

Text #18

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0604. Min Act: -0.0001

Data Index: 27904 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0604. Min Act: -0.0001

Data Index: 556073 (C4 (Web Text))

Max Activating Token Index: 648