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

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

Neuron 4504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0439. Min Range: -1.0439

Max Act: 1.0439. Min Act: -0.0002

Data Index: 1485601 (Python Code)

Max Activating Token Index: 508

Text #1

Max Range: 1.0439. Min Range: -1.0439

Max Act: 1.0047. Min Act: -0.0002

Data Index: 1620265 (Python Code)

Max Activating Token Index: 439

Text #2

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.8884. Min Act: -0.0002

Data Index: 1082987 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.8546. Min Act: -0.0002

Data Index: 1554393 (Python Code)

Max Activating Token Index: 345

Text #4

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7800. Min Act: -0.0002

Data Index: 1478508 (Python Code)

Max Activating Token Index: 375

Text #5

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.8225. Min Act: -0.0002

Data Index: 1539419 (Python Code)

Max Activating Token Index: 164

Text #6

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7501. Min Act: -0.0002

Data Index: 1545584 (Python Code)

Max Activating Token Index: 655

Text #7

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7807. Min Act: -0.0002

Data Index: 1540289 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7908. Min Act: -0.0002

Data Index: 1453663 (Python Code)

Max Activating Token Index: 734

Text #9

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7435. Min Act: -0.0002

Data Index: 1522792 (Python Code)

Max Activating Token Index: 507

Text #10

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7337. Min Act: -0.0002

Data Index: 1368718 (Python Code)

Max Activating Token Index: 344

Text #11

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7324. Min Act: -0.0002

Data Index: 1643908 (Python Code)

Max Activating Token Index: 639

Text #12

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7244. Min Act: -0.0002

Data Index: 1483239 (Python Code)

Max Activating Token Index: 403

Text #13

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7215. Min Act: -0.0002

Data Index: 1378839 (Python Code)

Max Activating Token Index: 578

Text #14

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7360. Min Act: -0.0002

Data Index: 1648483 (Python Code)

Max Activating Token Index: 458

Text #15

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7315. Min Act: -0.0002

Data Index: 364723 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7051. Min Act: -0.0002

Data Index: 1610381 (Python Code)

Max Activating Token Index: 141

Text #17

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7218. Min Act: -0.0002

Data Index: 1464796 (Python Code)

Max Activating Token Index: 545

Text #18

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.6989. Min Act: -0.0002

Data Index: 1433766 (Python Code)

Max Activating Token Index: 564

Text #19

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7226. Min Act: -0.0002

Data Index: 1487206 (Python Code)

Max Activating Token Index: 982