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

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

Neuron 3104 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1546873 (Python Code)

Max Activating Token Index: 385

Text #1

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1620289 (Python Code)

Max Activating Token Index: 569

Text #2

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1625024 (Python Code)

Max Activating Token Index: 737

Text #3

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2742. Min Act: -0.0000

Data Index: 103822 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1592569 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1652635 (Python Code)

Max Activating Token Index: 777

Text #6

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2513. Min Act: 0.0000

Data Index: 395277 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1557457 (Python Code)

Max Activating Token Index: 987

Text #8

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1071715 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2338. Min Act: -0.0000

Data Index: 698519 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1030070 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1159245 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1375102 (Python Code)

Max Activating Token Index: 431

Text #13

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2265. Min Act: -0.0000

Data Index: 22326 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1620288 (Python Code)

Max Activating Token Index: 706

Text #15

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2053. Min Act: 0.0000

Data Index: 894556 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2110. Min Act: -0.0000

Data Index: 571589 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1640818 (Python Code)

Max Activating Token Index: 874

Text #18

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1451214 (Python Code)

Max Activating Token Index: 341

Text #19

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1589818 (Python Code)

Max Activating Token Index: 259