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

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

Neuron 2829 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: 0.6608. Min Range: -0.6608

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1462235 (Python Code)

Max Activating Token Index: 462

Text #1

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1553428 (Python Code)

Max Activating Token Index: 743

Text #2

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1587201 (Python Code)

Max Activating Token Index: 812

Text #3

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1420741 (Python Code)

Max Activating Token Index: 586

Text #4

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1656873 (Python Code)

Max Activating Token Index: 673

Text #5

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1537775 (Python Code)

Max Activating Token Index: 111

Text #6

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1459123 (Python Code)

Max Activating Token Index: 746

Text #7

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1584669 (Python Code)

Max Activating Token Index: 562

Text #8

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1515416 (Python Code)

Max Activating Token Index: 105

Text #9

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1465357 (Python Code)

Max Activating Token Index: 768

Text #10

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1627719 (Python Code)

Max Activating Token Index: 803

Text #11

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1501976 (Python Code)

Max Activating Token Index: 582

Text #12

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1584411 (Python Code)

Max Activating Token Index: 420

Text #13

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1491193 (Python Code)

Max Activating Token Index: 594

Text #14

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1422151 (Python Code)

Max Activating Token Index: 964

Text #15

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1606354 (Python Code)

Max Activating Token Index: 79

Text #16

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1471848 (Python Code)

Max Activating Token Index: 108

Text #17

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1618424 (Python Code)

Max Activating Token Index: 275

Text #18

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1569080 (Python Code)

Max Activating Token Index: 584

Text #19

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1384015 (Python Code)

Max Activating Token Index: 809