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

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

Neuron 4425 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: 1.5336. Min Range: -1.5336

Max Act: 1.5336. Min Act: -0.0000

Data Index: 1410450 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.3476. Min Act: -0.0000

Data Index: 1449393 (Python Code)

Max Activating Token Index: 651

Text #2

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.3747. Min Act: -0.0000

Data Index: 1373467 (Python Code)

Max Activating Token Index: 101

Text #3

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.3914. Min Act: -0.0000

Data Index: 1541351 (Python Code)

Max Activating Token Index: 830

Text #4

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.1757. Min Act: -0.0000

Data Index: 1544930 (Python Code)

Max Activating Token Index: 163

Text #5

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1488593 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1521429 (Python Code)

Max Activating Token Index: 253

Text #7

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.1620. Min Act: -0.0000

Data Index: 1656473 (Python Code)

Max Activating Token Index: 381

Text #8

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1588668 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1392424 (Python Code)

Max Activating Token Index: 259

Text #10

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1599461 (Python Code)

Max Activating Token Index: 818

Text #11

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.1275. Min Act: -0.0000

Data Index: 1423646 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1647098 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1573119 (Python Code)

Max Activating Token Index: 850

Text #14

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1405040 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.0797. Min Act: -0.0000

Data Index: 1370576 (Python Code)

Max Activating Token Index: 320

Text #16

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1484429 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1476696 (Python Code)

Max Activating Token Index: 182

Text #18

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.1298. Min Act: -0.0000

Data Index: 1614772 (Python Code)

Max Activating Token Index: 572

Text #19

Max Range: 1.5336. Min Range: -1.5336

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1638916 (Python Code)

Max Activating Token Index: 959