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

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

Neuron 1318 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1614387 (Python Code)

Max Activating Token Index: 697

Text #1

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1563167 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1514593 (Python Code)

Max Activating Token Index: 988

Text #3

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1488418 (Python Code)

Max Activating Token Index: 330

Text #4

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1605100 (Python Code)

Max Activating Token Index: 182

Text #5

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1552642 (Python Code)

Max Activating Token Index: 764

Text #6

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1538873 (Python Code)

Max Activating Token Index: 546

Text #7

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1410189 (Python Code)

Max Activating Token Index: 882

Text #8

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1412436 (Python Code)

Max Activating Token Index: 871

Text #9

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1367637 (Python Code)

Max Activating Token Index: 585

Text #10

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1440569 (Python Code)

Max Activating Token Index: 925

Text #11

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1439009 (Python Code)

Max Activating Token Index: 386

Text #12

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1614410 (Python Code)

Max Activating Token Index: 418

Text #13

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1437826 (Python Code)

Max Activating Token Index: 169

Text #14

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1511341 (Python Code)

Max Activating Token Index: 420

Text #15

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1486659 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1569006 (Python Code)

Max Activating Token Index: 700

Text #17

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1396908 (Python Code)

Max Activating Token Index: 281

Text #18

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1385118 (Python Code)

Max Activating Token Index: 630

Text #19

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1472176 (Python Code)

Max Activating Token Index: 107