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

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

Neuron 2003 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: 0.0633. Min Range: -0.0633

Max Act: 0.0631. Min Act: -0.0002

Data Index: 599248 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0002

Data Index: 321188 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0602. Min Act: -0.0002

Data Index: 493459 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1309721 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1335585 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0568. Min Act: -0.0002

Data Index: 725826 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1318791 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0537. Min Act: -0.0002

Data Index: 745755 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0542. Min Act: -0.0002

Data Index: 678133 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1056594 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0513. Min Act: -0.0002

Data Index: 403560 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0517. Min Act: -0.0002

Data Index: 955000 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0511. Min Act: -0.0002

Data Index: 768652 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0520. Min Act: -0.0002

Data Index: 257618 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0506. Min Act: -0.0002

Data Index: 171290 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0506. Min Act: -0.0002

Data Index: 896383 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1343469 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0504. Min Act: -0.0002

Data Index: 628679 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0499. Min Act: -0.0002

Data Index: 445990 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0516. Min Act: -0.0002

Data Index: 46824 (C4 (Web Text))

Max Activating Token Index: 23