Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1498 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0001

Data Index: 342054 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0502. Min Act: -0.0002

Data Index: 8131 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1082037 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0419. Min Act: -0.0002

Data Index: 611471 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1174980 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0444. Min Act: -0.0002

Data Index: 379531 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0436. Min Act: -0.0001

Data Index: 141477 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0403. Min Act: -0.0002

Data Index: 370934 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1655661 (Python Code)

Max Activating Token Index: 648

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0396. Min Act: -0.0002

Data Index: 726583 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1164411 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1181557 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0352. Min Act: -0.0002

Data Index: 19028 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1040164 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0335. Min Act: -0.0002

Data Index: 975853 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0358. Min Act: -0.0003

Data Index: 607146 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0350. Min Act: -0.0003

Data Index: 12655 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0364. Min Act: -0.0002

Data Index: 132483 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1299419 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1122733 (C4 (Web Text))

Max Activating Token Index: 924