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

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

Neuron 1209 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1559084 (Python Code)

Max Activating Token Index: 162

Text #1

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1645623 (Python Code)

Max Activating Token Index: 205

Text #2

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1403361 (Python Code)

Max Activating Token Index: 411

Text #3

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1403244 (Python Code)

Max Activating Token Index: 564

Text #4

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1592418 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1508011 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1602754 (Python Code)

Max Activating Token Index: 227

Text #7

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1647503 (Python Code)

Max Activating Token Index: 372

Text #8

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1629673 (Python Code)

Max Activating Token Index: 227

Text #9

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1624744 (Python Code)

Max Activating Token Index: 505

Text #10

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1403364 (Python Code)

Max Activating Token Index: 862

Text #11

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1517935 (Python Code)

Max Activating Token Index: 259

Text #12

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1437472 (Python Code)

Max Activating Token Index: 788

Text #13

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1516121 (Python Code)

Max Activating Token Index: 518

Text #14

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1573972 (Python Code)

Max Activating Token Index: 822

Text #15

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1419002 (Python Code)

Max Activating Token Index: 688

Text #16

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1486572 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1485306 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1389619 (Python Code)

Max Activating Token Index: 445

Text #19

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1511897 (Python Code)

Max Activating Token Index: 914