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

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

Neuron 839 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: 0.0553. Min Range: -0.0553

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1617748 (Python Code)

Max Activating Token Index: 716

Text #1

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1508477 (Python Code)

Max Activating Token Index: 435

Text #2

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1418190 (Python Code)

Max Activating Token Index: 101

Text #3

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1556875 (Python Code)

Max Activating Token Index: 857

Text #4

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1376175 (Python Code)

Max Activating Token Index: 358

Text #5

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1538058 (Python Code)

Max Activating Token Index: 477

Text #6

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1401742 (Python Code)

Max Activating Token Index: 550

Text #7

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1453161 (Python Code)

Max Activating Token Index: 200

Text #8

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1409316 (Python Code)

Max Activating Token Index: 362

Text #9

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1654872 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1369891 (Python Code)

Max Activating Token Index: 49

Text #11

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1575185 (Python Code)

Max Activating Token Index: 389

Text #12

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1568018 (Python Code)

Max Activating Token Index: 385

Text #13

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1394243 (Python Code)

Max Activating Token Index: 440

Text #14

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1387052 (Python Code)

Max Activating Token Index: 682

Text #15

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1375713 (Python Code)

Max Activating Token Index: 655

Text #16

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1590689 (Python Code)

Max Activating Token Index: 321

Text #17

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1592825 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1571987 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1553624 (Python Code)

Max Activating Token Index: 175