Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3438 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1492778 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1569318 (Python Code)

Max Activating Token Index: 930

Text #2

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1461711 (Python Code)

Max Activating Token Index: 956

Text #3

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1381876 (Python Code)

Max Activating Token Index: 648

Text #4

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1394924 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1473165 (Python Code)

Max Activating Token Index: 959

Text #6

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1482046 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1533679 (Python Code)

Max Activating Token Index: 55

Text #8

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0327. Min Act: -0.0004

Data Index: 1588374 (Python Code)

Max Activating Token Index: 349

Text #9

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1393125 (Python Code)

Max Activating Token Index: 492

Text #10

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1573512 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1563621 (Python Code)

Max Activating Token Index: 81

Text #12

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1452865 (Python Code)

Max Activating Token Index: 64

Text #13

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1595977 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1470132 (Python Code)

Max Activating Token Index: 708

Text #15

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1518496 (Python Code)

Max Activating Token Index: 928

Text #16

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1481899 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1497402 (Python Code)

Max Activating Token Index: 331

Text #18

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0273. Min Act: -0.0003

Data Index: 1531462 (Python Code)

Max Activating Token Index: 692

Text #19

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1604247 (Python Code)

Max Activating Token Index: 65