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

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

Neuron 5527 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.2422. Min Act: -0.0000

Data Index: 1581819 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.1309. Min Act: -0.0000

Data Index: 1375789 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.0023. Min Act: -0.0000

Data Index: 1628060 (Python Code)

Max Activating Token Index: 386

Text #3

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.1345. Min Act: -0.0001

Data Index: 1507777 (Python Code)

Max Activating Token Index: 473

Text #4

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1555078 (Python Code)

Max Activating Token Index: 665

Text #5

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.1538. Min Act: -0.0000

Data Index: 1585834 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1647880 (Python Code)

Max Activating Token Index: 748

Text #7

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.0327. Min Act: -0.0001

Data Index: 1502169 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1373745 (Python Code)

Max Activating Token Index: 775

Text #9

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.0224. Min Act: -0.0001

Data Index: 1469893 (Python Code)

Max Activating Token Index: 585

Text #10

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.0536. Min Act: -0.0000

Data Index: 1528778 (Python Code)

Max Activating Token Index: 858

Text #11

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.1065. Min Act: -0.0001

Data Index: 1568597 (Python Code)

Max Activating Token Index: 768

Text #12

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.9770. Min Act: -0.0000

Data Index: 1407901 (Python Code)

Max Activating Token Index: 429

Text #13

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.9524. Min Act: -0.0001

Data Index: 1464556 (Python Code)

Max Activating Token Index: 259

Text #14

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.0100. Min Act: -0.0001

Data Index: 1564921 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1450061 (Python Code)

Max Activating Token Index: 674

Text #16

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1627837 (Python Code)

Max Activating Token Index: 355

Text #17

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.0424. Min Act: -0.0000

Data Index: 1476363 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.8901. Min Act: -0.0001

Data Index: 1654801 (Python Code)

Max Activating Token Index: 720

Text #19

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1510668 (Python Code)

Max Activating Token Index: 324