Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1080 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1686. Min Act: -0.0002

Data Index: 349954 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1735. Min Act: -0.0002

Data Index: 251953 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1684. Min Act: -0.0002

Data Index: 1006337 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1686. Min Act: -0.0002

Data Index: 516140 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1682. Min Act: -0.0002

Data Index: 1337914 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1623. Min Act: -0.0003

Data Index: 301631 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1579. Min Act: -0.0002

Data Index: 414662 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1561. Min Act: -0.0002

Data Index: 867827 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1576. Min Act: -0.0001

Data Index: 234758 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1603. Min Act: -0.0002

Data Index: 703764 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1587. Min Act: -0.0002

Data Index: 130448 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1556. Min Act: -0.0002

Data Index: 997074 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1621. Min Act: -0.0002

Data Index: 871569 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1531. Min Act: -0.0002

Data Index: 123356 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1552. Min Act: -0.0002

Data Index: 907300 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1498. Min Act: -0.0002

Data Index: 1000199 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1560. Min Act: -0.0002

Data Index: 316570 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1605. Min Act: -0.0002

Data Index: 93266 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1544. Min Act: -0.0002

Data Index: 777669 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1508. Min Act: -0.0002

Data Index: 186572 (C4 (Web Text))

Max Activating Token Index: 279