Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1720 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1562505 (Python Code)

Max Activating Token Index: 834

Text #1

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0709. Min Act: -0.0003

Data Index: 1559140 (Python Code)

Max Activating Token Index: 305

Text #2

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1521155 (Python Code)

Max Activating Token Index: 470

Text #3

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1629937 (Python Code)

Max Activating Token Index: 140

Text #4

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1477247 (Python Code)

Max Activating Token Index: 216

Text #5

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1483527 (Python Code)

Max Activating Token Index: 381

Text #6

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1362520 (Python Code)

Max Activating Token Index: 887

Text #7

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1404030 (Python Code)

Max Activating Token Index: 300

Text #8

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1620946 (Python Code)

Max Activating Token Index: 197

Text #9

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1606118 (Python Code)

Max Activating Token Index: 140

Text #10

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1570881 (Python Code)

Max Activating Token Index: 542

Text #11

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1468724 (Python Code)

Max Activating Token Index: 297

Text #12

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1535961 (Python Code)

Max Activating Token Index: 817

Text #13

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1559768 (Python Code)

Max Activating Token Index: 415

Text #14

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1369619 (Python Code)

Max Activating Token Index: 624

Text #15

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1527330 (Python Code)

Max Activating Token Index: 190

Text #16

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1449843 (Python Code)

Max Activating Token Index: 740

Text #17

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1642429 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1477728 (Python Code)

Max Activating Token Index: 662

Text #19

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1553183 (Python Code)

Max Activating Token Index: 430