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

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

Neuron 3749 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1898. Min Act: -0.0001

Data Index: 1315667 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1611928 (Python Code)

Max Activating Token Index: 276

Text #2

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1784. Min Act: -0.0001

Data Index: 900642 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1739. Min Act: -0.0001

Data Index: 605344 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1727. Min Act: -0.0001

Data Index: 1629087 (Python Code)

Max Activating Token Index: 763

Text #5

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1684. Min Act: -0.0001

Data Index: 559607 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1616. Min Act: -0.0001

Data Index: 67635 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1644. Min Act: -0.0001

Data Index: 1055539 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1614. Min Act: -0.0001

Data Index: 206536 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1069479 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1301872 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1561. Min Act: -0.0001

Data Index: 309371 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1561028 (Python Code)

Max Activating Token Index: 794

Text #13

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1486364 (Python Code)

Max Activating Token Index: 743

Text #14

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1616041 (Python Code)

Max Activating Token Index: 976

Text #15

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1184120 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1510. Min Act: -0.0001

Data Index: 313798 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1447007 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1487. Min Act: -0.0001

Data Index: 295681 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1541667 (Python Code)

Max Activating Token Index: 768