Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 951 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1445942 (Python Code)

Max Activating Token Index: 266

Text #1

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1531983 (Python Code)

Max Activating Token Index: 789

Text #2

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1388482 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1571717 (Python Code)

Max Activating Token Index: 513

Text #4

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1416040 (Python Code)

Max Activating Token Index: 524

Text #5

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1439008 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0769. Min Act: -0.0001

Data Index: 174317 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1027079 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1553191 (Python Code)

Max Activating Token Index: 248

Text #9

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1654033 (Python Code)

Max Activating Token Index: 242

Text #10

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0653. Min Act: -0.0000

Data Index: 646439 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0663. Min Act: -0.0000

Data Index: 412089 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1404091 (Python Code)

Max Activating Token Index: 581

Text #13

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0590. Min Act: -0.0000

Data Index: 132695 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1061443 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0589. Min Act: -0.0000

Data Index: 442838 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1516246 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1589002 (Python Code)

Max Activating Token Index: 739

Text #18

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0589. Min Act: -0.0000

Data Index: 1656429 (Python Code)

Max Activating Token Index: 256

Text #19

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1518526 (Python Code)

Max Activating Token Index: 563