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

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

Neuron 1777 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0490. Min Act: -0.0005

Data Index: 1333537 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0496. Min Act: -0.0005

Data Index: 90891 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0468. Min Act: -0.0005

Data Index: 545553 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0467. Min Act: -0.0005

Data Index: 999502 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0482. Min Act: -0.0005

Data Index: 1300055 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0457. Min Act: -0.0005

Data Index: 1254719 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0464. Min Act: -0.0005

Data Index: 691312 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0468. Min Act: -0.0005

Data Index: 957204 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0475. Min Act: -0.0005

Data Index: 764373 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0442. Min Act: -0.0005

Data Index: 264005 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0440. Min Act: -0.0005

Data Index: 1005119 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0429. Min Act: -0.0005

Data Index: 443874 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0431. Min Act: -0.0005

Data Index: 451999 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0426. Min Act: -0.0005

Data Index: 1103742 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0460. Min Act: -0.0005

Data Index: 936164 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0447. Min Act: -0.0005

Data Index: 1037437 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0431. Min Act: -0.0005

Data Index: 10601 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0442. Min Act: -0.0005

Data Index: 285746 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0433. Min Act: -0.0005

Data Index: 786240 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0441. Min Act: -0.0005

Data Index: 1195530 (C4 (Web Text))

Max Activating Token Index: 531