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

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

Neuron 2548 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3760. Min Act: -0.0000

Data Index: 1644905 (Python Code)

Max Activating Token Index: 867

Text #1

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1367096 (Python Code)

Max Activating Token Index: 646

Text #2

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3259. Min Act: 0.0000

Data Index: 1524366 (Python Code)

Max Activating Token Index: 556

Text #3

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3873. Min Act: 0.0000

Data Index: 1379765 (Python Code)

Max Activating Token Index: 846

Text #4

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2293. Min Act: -0.0000

Data Index: 1613561 (Python Code)

Max Activating Token Index: 717

Text #5

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1645243 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0814. Min Act: 0.0000

Data Index: 1490216 (Python Code)

Max Activating Token Index: 127

Text #7

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1451345 (Python Code)

Max Activating Token Index: 689

Text #8

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0522. Min Act: -0.0000

Data Index: 1462426 (Python Code)

Max Activating Token Index: 930

Text #9

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1450288 (Python Code)

Max Activating Token Index: 978

Text #10

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.9267. Min Act: 0.0000

Data Index: 1562387 (Python Code)

Max Activating Token Index: 571

Text #11

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.9535. Min Act: 0.0000

Data Index: 1396506 (Python Code)

Max Activating Token Index: 458

Text #12

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1374287 (Python Code)

Max Activating Token Index: 329

Text #13

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1532129 (Python Code)

Max Activating Token Index: 386

Text #14

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.9619. Min Act: 0.0000

Data Index: 1429485 (Python Code)

Max Activating Token Index: 799

Text #15

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1647532 (Python Code)

Max Activating Token Index: 217

Text #16

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1395621 (Python Code)

Max Activating Token Index: 651

Text #17

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1420052 (Python Code)

Max Activating Token Index: 806

Text #18

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.8329. Min Act: 0.0000

Data Index: 1360398 (Python Code)

Max Activating Token Index: 895

Text #19

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1610353 (Python Code)

Max Activating Token Index: 206