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

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

Neuron 5827 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0463. Min Act: -0.0002

Data Index: 725747 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0499. Min Act: -0.0002

Data Index: 932042 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0499. Min Act: -0.0002

Data Index: 318306 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1189768 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1276827 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0454. Min Act: -0.0002

Data Index: 281908 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0458. Min Act: -0.0002

Data Index: 610828 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0417. Min Act: -0.0002

Data Index: 946793 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0420. Min Act: -0.0002

Data Index: 211102 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0380. Min Act: -0.0002

Data Index: 827544 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1284936 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0394. Min Act: -0.0002

Data Index: 571481 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0376. Min Act: -0.0002

Data Index: 290118 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1453920 (Python Code)

Max Activating Token Index: 438

Text #14

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0363. Min Act: -0.0002

Data Index: 988313 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0381. Min Act: -0.0002

Data Index: 280864 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0373. Min Act: -0.0002

Data Index: 411749 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1224882 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0359. Min Act: -0.0002

Data Index: 479966 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1083944 (C4 (Web Text))

Max Activating Token Index: 350