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

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

Neuron 2358 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2425. Min Act: -0.0001

Data Index: 605661 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.2232. Min Act: -0.0001

Data Index: 528098 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1885. Min Act: -0.0001

Data Index: 437950 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1839. Min Act: -0.0001

Data Index: 1158431 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1766. Min Act: -0.0001

Data Index: 1153571 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1644. Min Act: -0.0001

Data Index: 873533 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1816. Min Act: -0.0001

Data Index: 491362 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1737. Min Act: -0.0001

Data Index: 649512 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1726. Min Act: -0.0001

Data Index: 1083625 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1730. Min Act: -0.0001

Data Index: 253898 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1714. Min Act: -0.0001

Data Index: 731308 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1592. Min Act: -0.0001

Data Index: 531603 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1171703 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1621. Min Act: -0.0001

Data Index: 1344388 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1182082 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1502. Min Act: -0.0001

Data Index: 616298 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1650. Min Act: -0.0001

Data Index: 994759 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1595. Min Act: -0.0001

Data Index: 516699 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1581. Min Act: -0.0001

Data Index: 672110 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.2425. Min Range: -0.2425

Max Act: 0.1448. Min Act: -0.0001

Data Index: 812342 (C4 (Web Text))

Max Activating Token Index: 822