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

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

Neuron 589 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: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0002

Data Index: 875294 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0531. Min Act: -0.0002

Data Index: 951542 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0483. Min Act: -0.0002

Data Index: 530227 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0477. Min Act: -0.0002

Data Index: 192109 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0474. Min Act: -0.0002

Data Index: 616335 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1110430 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0454. Min Act: -0.0002

Data Index: 672973 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0427. Min Act: -0.0002

Data Index: 148845 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0438. Min Act: -0.0002

Data Index: 971355 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0394. Min Act: -0.0002

Data Index: 377448 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0429. Min Act: -0.0002

Data Index: 424646 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0378. Min Act: -0.0002

Data Index: 915544 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0407. Min Act: -0.0002

Data Index: 265917 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0398. Min Act: -0.0002

Data Index: 272676 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0384. Min Act: -0.0002

Data Index: 974125 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0411. Min Act: -0.0002

Data Index: 381426 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1113450 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0413. Min Act: -0.0002

Data Index: 428171 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1614219 (Python Code)

Max Activating Token Index: 360

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0361. Min Act: -0.0002

Data Index: 290920 (C4 (Web Text))

Max Activating Token Index: 410