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

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

Neuron 1275 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: 0.2571. Min Range: -0.2571

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1487531 (Python Code)

Max Activating Token Index: 760

Text #1

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1365226 (Python Code)

Max Activating Token Index: 498

Text #2

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1649651 (Python Code)

Max Activating Token Index: 577

Text #3

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2336. Min Act: -0.0000

Data Index: 148627 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2526. Min Act: -0.0000

Data Index: 246298 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1466560 (Python Code)

Max Activating Token Index: 626

Text #6

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1524359 (Python Code)

Max Activating Token Index: 633

Text #7

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1523518 (Python Code)

Max Activating Token Index: 753

Text #8

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1643064 (Python Code)

Max Activating Token Index: 927

Text #9

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1403232 (Python Code)

Max Activating Token Index: 821

Text #10

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1650761 (Python Code)

Max Activating Token Index: 441

Text #11

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1480429 (Python Code)

Max Activating Token Index: 259

Text #12

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1461122 (Python Code)

Max Activating Token Index: 916

Text #13

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1405237 (Python Code)

Max Activating Token Index: 113

Text #14

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1431397 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1602007 (Python Code)

Max Activating Token Index: 939

Text #16

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2113. Min Act: -0.0001

Data Index: 1591928 (Python Code)

Max Activating Token Index: 369

Text #17

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1535911 (Python Code)

Max Activating Token Index: 853

Text #18

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1647786 (Python Code)

Max Activating Token Index: 435

Text #19

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1444915 (Python Code)

Max Activating Token Index: 616