Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0003

Data Index: 315901 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0517. Min Act: -0.0003

Data Index: 613771 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0448. Min Act: -0.0003

Data Index: 862788 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1283187 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0446. Min Act: -0.0003

Data Index: 562545 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1268769 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1079383 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0430. Min Act: -0.0003

Data Index: 392233 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0436. Min Act: -0.0003

Data Index: 417003 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0423. Min Act: -0.0003

Data Index: 481471 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0413. Min Act: -0.0003

Data Index: 2038 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0437. Min Act: -0.0003

Data Index: 102593 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0402. Min Act: -0.0003

Data Index: 109005 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1329184 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1130808 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0407. Min Act: -0.0003

Data Index: 640492 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0412. Min Act: -0.0002

Data Index: 186298 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0394. Min Act: -0.0002

Data Index: 729326 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0386. Min Act: -0.0003

Data Index: 511690 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0389. Min Act: -0.0003

Data Index: 930118 (C4 (Web Text))

Max Activating Token Index: 934