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

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

Neuron 4123 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: 0.0635. Min Range: -0.0635

Max Act: 0.0635. Min Act: -0.0002

Data Index: 558470 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0544. Min Act: -0.0002

Data Index: 583079 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0540. Min Act: -0.0002

Data Index: 968989 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1158549 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0534. Min Act: -0.0002

Data Index: 687430 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0533. Min Act: -0.0002

Data Index: 939799 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0521. Min Act: -0.0002

Data Index: 995522 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1178748 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1115118 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0499. Min Act: -0.0002

Data Index: 876833 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0498. Min Act: -0.0002

Data Index: 601239 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1305566 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0487. Min Act: -0.0002

Data Index: 500434 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0485. Min Act: -0.0002

Data Index: 840525 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0483. Min Act: -0.0002

Data Index: 848982 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0477. Min Act: -0.0002

Data Index: 621910 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0483. Min Act: -0.0002

Data Index: 398316 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0475. Min Act: -0.0002

Data Index: 696098 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1039411 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0470. Min Act: -0.0003

Data Index: 301586 (C4 (Web Text))

Max Activating Token Index: 884