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

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

Neuron 1328 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: 0.2900. Min Range: -0.2900

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1405855 (Python Code)

Max Activating Token Index: 665

Text #1

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1641386 (Python Code)

Max Activating Token Index: 796

Text #2

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1595371 (Python Code)

Max Activating Token Index: 311

Text #3

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1616254 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1641468 (Python Code)

Max Activating Token Index: 863

Text #5

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1384144 (Python Code)

Max Activating Token Index: 759

Text #6

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1375150 (Python Code)

Max Activating Token Index: 481

Text #7

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1466698 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1615209 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2399. Min Act: -0.0000

Data Index: 1423402 (Python Code)

Max Activating Token Index: 887

Text #10

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1604223 (Python Code)

Max Activating Token Index: 624

Text #11

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1586479 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1417269 (Python Code)

Max Activating Token Index: 335

Text #13

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1523577 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1368236 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1561490 (Python Code)

Max Activating Token Index: 573

Text #16

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1414961 (Python Code)

Max Activating Token Index: 216

Text #17

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1647019 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1584281 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1634038 (Python Code)

Max Activating Token Index: 903