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

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

Neuron 1627 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: 0.0546. Min Range: -0.0546

Max Act: 0.0487. Min Act: -0.0002

Data Index: 383554 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0330. Min Act: -0.0002

Data Index: 764777 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1255302 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1533527 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0507. Min Act: -0.0002

Data Index: 827337 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0492. Min Act: -0.0002

Data Index: 223732 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1521555 (Python Code)

Max Activating Token Index: 289

Text #7

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1257448 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1413623 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0499. Min Act: -0.0002

Data Index: 94685 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1481822 (Python Code)

Max Activating Token Index: 354

Text #11

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1399912 (Python Code)

Max Activating Token Index: 595

Text #12

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0428. Min Act: -0.0002

Data Index: 29455 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1556490 (Python Code)

Max Activating Token Index: 132

Text #14

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0381. Min Act: -0.0002

Data Index: 498657 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1164792 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0420. Min Act: -0.0002

Data Index: 347114 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1125571 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1134491 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1531909 (Python Code)

Max Activating Token Index: 435