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

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

Neuron 4536 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1621346 (Python Code)

Max Activating Token Index: 346

Text #1

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.6868. Min Act: -0.0000

Data Index: 1593913 (Python Code)

Max Activating Token Index: 273

Text #2

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.4274. Min Act: -0.0000

Data Index: 1497460 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.4984. Min Act: -0.0000

Data Index: 1588427 (Python Code)

Max Activating Token Index: 720

Text #4

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.4226. Min Act: -0.0000

Data Index: 1541909 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.3654. Min Act: -0.0000

Data Index: 1378483 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.3063. Min Act: -0.0000

Data Index: 1618389 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.1886. Min Act: -0.0000

Data Index: 1604507 (Python Code)

Max Activating Token Index: 902

Text #8

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.3267. Min Act: -0.0000

Data Index: 1604735 (Python Code)

Max Activating Token Index: 265

Text #9

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.3502. Min Act: -0.0000

Data Index: 1530651 (Python Code)

Max Activating Token Index: 371

Text #10

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.2176. Min Act: -0.0000

Data Index: 1443097 (Python Code)

Max Activating Token Index: 338

Text #11

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1487627 (Python Code)

Max Activating Token Index: 319

Text #12

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1566453 (Python Code)

Max Activating Token Index: 778

Text #13

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.1453. Min Act: -0.0000

Data Index: 1540155 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.0665. Min Act: -0.0000

Data Index: 1380212 (Python Code)

Max Activating Token Index: 945

Text #15

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.1348. Min Act: -0.0000

Data Index: 1461700 (Python Code)

Max Activating Token Index: 911

Text #16

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.1326. Min Act: -0.0000

Data Index: 1433085 (Python Code)

Max Activating Token Index: 998

Text #17

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1416643 (Python Code)

Max Activating Token Index: 690

Text #18

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1410039 (Python Code)

Max Activating Token Index: 439

Text #19

Max Range: 1.7003. Min Range: -1.7003

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1575554 (Python Code)

Max Activating Token Index: 353