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

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

Neuron 5448 in Layer 1

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: 0.0602. Min Range: -0.0602

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1650225 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1404301 (Python Code)

Max Activating Token Index: 977

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1436672 (Python Code)

Max Activating Token Index: 910

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1386675 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1547444 (Python Code)

Max Activating Token Index: 349

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1591758 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1401537 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1574843 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1598012 (Python Code)

Max Activating Token Index: 191

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1393009 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1652754 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1513144 (Python Code)

Max Activating Token Index: 612

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1526186 (Python Code)

Max Activating Token Index: 794

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1485231 (Python Code)

Max Activating Token Index: 894

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1388145 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1466352 (Python Code)

Max Activating Token Index: 742

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1649687 (Python Code)

Max Activating Token Index: 1015

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1576109 (Python Code)

Max Activating Token Index: 254

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1420564 (Python Code)

Max Activating Token Index: 547

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1426876 (Python Code)

Max Activating Token Index: 567