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

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

Neuron 2253 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8919. Min Act: -0.0001

Data Index: 1471059 (Python Code)

Max Activating Token Index: 195

Text #1

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8769. Min Act: -0.0001

Data Index: 1390712 (Python Code)

Max Activating Token Index: 284

Text #2

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8475. Min Act: -0.0001

Data Index: 1482857 (Python Code)

Max Activating Token Index: 557

Text #3

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8404. Min Act: -0.0001

Data Index: 1453627 (Python Code)

Max Activating Token Index: 961

Text #4

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.7828. Min Act: -0.0001

Data Index: 1608863 (Python Code)

Max Activating Token Index: 660

Text #5

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.9545. Min Act: -0.0001

Data Index: 1562156 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8354. Min Act: -0.0001

Data Index: 1475548 (Python Code)

Max Activating Token Index: 241

Text #7

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8330. Min Act: -0.0001

Data Index: 1642626 (Python Code)

Max Activating Token Index: 860

Text #8

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8893. Min Act: -0.0001

Data Index: 1460950 (Python Code)

Max Activating Token Index: 832

Text #9

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8314. Min Act: -0.0001

Data Index: 1391984 (Python Code)

Max Activating Token Index: 951

Text #10

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8249. Min Act: -0.0001

Data Index: 1463981 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8117. Min Act: -0.0001

Data Index: 1380473 (Python Code)

Max Activating Token Index: 444

Text #12

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8072. Min Act: -0.0001

Data Index: 1540910 (Python Code)

Max Activating Token Index: 522

Text #13

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8215. Min Act: -0.0001

Data Index: 1552078 (Python Code)

Max Activating Token Index: 1020

Text #14

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.7683. Min Act: -0.0000

Data Index: 1603997 (Python Code)

Max Activating Token Index: 562

Text #15

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8604. Min Act: -0.0000

Data Index: 1375799 (Python Code)

Max Activating Token Index: 501

Text #16

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8440. Min Act: -0.0001

Data Index: 1425777 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.7624. Min Act: -0.0001

Data Index: 1459178 (Python Code)

Max Activating Token Index: 482

Text #18

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8094. Min Act: -0.0001

Data Index: 1582438 (Python Code)

Max Activating Token Index: 829

Text #19

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8094. Min Act: -0.0001

Data Index: 1363453 (Python Code)

Max Activating Token Index: 401