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

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

Neuron 5067 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.2979. Min Act: -0.0001

Data Index: 679315 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.2912. Min Act: -0.0001

Data Index: 355799 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.1478. Min Act: -0.0001

Data Index: 1544159 (Python Code)

Max Activating Token Index: 664

Text #3

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.1570. Min Act: -0.0001

Data Index: 1492769 (Python Code)

Max Activating Token Index: 616

Text #4

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.1631. Min Act: -0.0000

Data Index: 822668 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.2428. Min Act: -0.0001

Data Index: 1622932 (Python Code)

Max Activating Token Index: 413

Text #6

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1410694 (Python Code)

Max Activating Token Index: 449

Text #7

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1281850 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.2216. Min Act: -0.0000

Data Index: 1539876 (Python Code)

Max Activating Token Index: 625

Text #9

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.1059. Min Act: -0.0001

Data Index: 1554221 (Python Code)

Max Activating Token Index: 519

Text #10

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.0833. Min Act: -0.0000

Data Index: 1495581 (Python Code)

Max Activating Token Index: 157

Text #11

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.1791. Min Act: -0.0001

Data Index: 1367643 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.1663. Min Act: -0.0001

Data Index: 1615632 (Python Code)

Max Activating Token Index: 560

Text #13

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.1285. Min Act: -0.0001

Data Index: 324970 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.0868. Min Act: -0.0001

Data Index: 1600893 (Python Code)

Max Activating Token Index: 549

Text #15

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.0446. Min Act: -0.0000

Data Index: 1446861 (Python Code)

Max Activating Token Index: 874

Text #16

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.0506. Min Act: -0.0001

Data Index: 1397112 (Python Code)

Max Activating Token Index: 845

Text #17

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.0430. Min Act: -0.0001

Data Index: 135963 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.1051. Min Act: -0.0001

Data Index: 1455021 (Python Code)

Max Activating Token Index: 265

Text #19

Max Range: 1.2979. Min Range: -1.2979

Max Act: 1.1450. Min Act: -0.0001

Data Index: 1614644 (Python Code)

Max Activating Token Index: 689