Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4737 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1251. Min Act: -0.0002

Data Index: 595697 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0569. Min Act: -0.0002

Data Index: 214351 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0608. Min Act: -0.0002

Data Index: 974092 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0517. Min Act: -0.0002

Data Index: 894608 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0584. Min Act: -0.0002

Data Index: 270549 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0507. Min Act: -0.0002

Data Index: 494644 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0525. Min Act: -0.0002

Data Index: 444608 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1177696 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1156355 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0511. Min Act: -0.0002

Data Index: 806831 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0473. Min Act: -0.0002

Data Index: 645418 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1339463 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0460. Min Act: -0.0002

Data Index: 205411 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0408. Min Act: -0.0002

Data Index: 579128 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0476. Min Act: -0.0002

Data Index: 877287 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0395. Min Act: -0.0002

Data Index: 622257 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1163013 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1180963 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1043669 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0466. Min Act: -0.0002

Data Index: 464095 (C4 (Web Text))

Max Activating Token Index: 120