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

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

Neuron 522 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0790. Min Act: -0.0000

Data Index: 137549 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1607602 (Python Code)

Max Activating Token Index: 826

Text #2

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1604373 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0637. Min Act: -0.0000

Data Index: 48994 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0603. Min Act: -0.0000

Data Index: 767649 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1459508 (Python Code)

Max Activating Token Index: 91

Text #6

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0597. Min Act: -0.0000

Data Index: 1440296 (Python Code)

Max Activating Token Index: 379

Text #7

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1555582 (Python Code)

Max Activating Token Index: 31

Text #8

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1649798 (Python Code)

Max Activating Token Index: 91

Text #9

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1445371 (Python Code)

Max Activating Token Index: 155

Text #10

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1379775 (Python Code)

Max Activating Token Index: 527

Text #11

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1181107 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1442598 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1439069 (Python Code)

Max Activating Token Index: 339

Text #14

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1528385 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1422949 (Python Code)

Max Activating Token Index: 863

Text #16

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0439. Min Act: -0.0000

Data Index: 986820 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1477784 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1428811 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0446. Min Act: -0.0000

Data Index: 1612853 (Python Code)

Max Activating Token Index: 694