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

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

Neuron 3521 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.3680. Min Act: -0.0000

Data Index: 1424002 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.2206. Min Act: -0.0000

Data Index: 1578766 (Python Code)

Max Activating Token Index: 728

Text #2

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.3048. Min Act: -0.0000

Data Index: 1227186 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1554330 (Python Code)

Max Activating Token Index: 546

Text #4

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1434152 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1615568 (Python Code)

Max Activating Token Index: 707

Text #6

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.2561. Min Act: -0.0000

Data Index: 1423481 (Python Code)

Max Activating Token Index: 336

Text #7

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1357971 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1364264 (Python Code)

Max Activating Token Index: 923

Text #9

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1601. Min Act: -0.0000

Data Index: 748860 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1345. Min Act: -0.0000

Data Index: 585080 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1612. Min Act: -0.0000

Data Index: 879894 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1496265 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1266. Min Act: -0.0000

Data Index: 225204 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1522. Min Act: -0.0000

Data Index: 1514819 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1022. Min Act: -0.0000

Data Index: 1637661 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1574359 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1040. Min Act: -0.0000

Data Index: 945007 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1150558 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1214. Min Act: -0.0000

Data Index: 1616832 (Python Code)

Max Activating Token Index: 513