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

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

Neuron 1070 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3909. Min Act: -0.0000

Data Index: 598813 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 4.3909. Min Range: -4.3909

Max Act: 1.5227. Min Act: -0.0000

Data Index: 484423 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1079897 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 4.3909. Min Range: -4.3909

Max Act: 1.1533. Min Act: -0.0000

Data Index: 748447 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1601658 (Python Code)

Max Activating Token Index: 500

Text #5

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1315412 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1420212 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1628458 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1509. Min Act: -0.0000

Data Index: 296419 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1646060 (Python Code)

Max Activating Token Index: 392

Text #10

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1597977 (Python Code)

Max Activating Token Index: 454

Text #11

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1504. Min Act: -0.0000

Data Index: 525242 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1384. Min Act: -0.0000

Data Index: 411269 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1418. Min Act: -0.0000

Data Index: 648588 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1456. Min Act: -0.0000

Data Index: 362770 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1551715 (Python Code)

Max Activating Token Index: 359

Text #16

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1436448 (Python Code)

Max Activating Token Index: 281

Text #17

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1391859 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1499963 (Python Code)

Max Activating Token Index: 773

Text #19

Max Range: 4.3909. Min Range: -4.3909

Max Act: 0.1381. Min Act: -0.0000

Data Index: 699387 (C4 (Web Text))

Max Activating Token Index: 267