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

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

Neuron 2662 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: 0.3133. Min Range: -0.3133

Max Act: 0.3133. Min Act: -0.0000

Data Index: 138696 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1519543 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2678. Min Act: -0.0001

Data Index: 1486497 (Python Code)

Max Activating Token Index: 151

Text #3

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1562813 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2578. Min Act: -0.0000

Data Index: 696671 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1583520 (Python Code)

Max Activating Token Index: 546

Text #6

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1315763 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1592659 (Python Code)

Max Activating Token Index: 938

Text #8

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1617935 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2586. Min Act: -0.0000

Data Index: 83300 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1445644 (Python Code)

Max Activating Token Index: 580

Text #11

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2500. Min Act: -0.0000

Data Index: 771859 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1580133 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1399852 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2540. Min Act: -0.0000

Data Index: 781954 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2416. Min Act: -0.0000

Data Index: 768178 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1549763 (Python Code)

Max Activating Token Index: 512

Text #17

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1532426 (Python Code)

Max Activating Token Index: 285

Text #18

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1550615 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1496660 (Python Code)

Max Activating Token Index: 248