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

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

Neuron 2452 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: 2.1988. Min Range: -2.1988

Max Act: 2.1988. Min Act: -0.0000

Data Index: 1587459 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 2.1988. Min Range: -2.1988

Max Act: 2.1761. Min Act: -0.0001

Data Index: 1471471 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 2.1988. Min Range: -2.1988

Max Act: 2.1724. Min Act: -0.0001

Data Index: 1372419 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 2.1988. Min Range: -2.1988

Max Act: 2.0383. Min Act: -0.0000

Data Index: 1625097 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 2.1988. Min Range: -2.1988

Max Act: 2.0148. Min Act: -0.0001

Data Index: 1574632 (Python Code)

Max Activating Token Index: 547

Text #5

Max Range: 2.1988. Min Range: -2.1988

Max Act: 2.0072. Min Act: -0.0000

Data Index: 1520614 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.9795. Min Act: -0.0000

Data Index: 1613395 (Python Code)

Max Activating Token Index: 141

Text #7

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.9742. Min Act: -0.0001

Data Index: 1569873 (Python Code)

Max Activating Token Index: 250

Text #8

Max Range: 2.1988. Min Range: -2.1988

Max Act: 2.0714. Min Act: -0.0000

Data Index: 1469289 (Python Code)

Max Activating Token Index: 78

Text #9

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.9829. Min Act: -0.0001

Data Index: 1532310 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.9817. Min Act: -0.0000

Data Index: 1474849 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.9697. Min Act: -0.0000

Data Index: 1629978 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.9546. Min Act: -0.0001

Data Index: 1620848 (Python Code)

Max Activating Token Index: 80

Text #13

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.9748. Min Act: -0.0000

Data Index: 1627124 (Python Code)

Max Activating Token Index: 171

Text #14

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.8493. Min Act: -0.0001

Data Index: 1374881 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.9571. Min Act: -0.0000

Data Index: 1391128 (Python Code)

Max Activating Token Index: 285

Text #16

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.9140. Min Act: -0.0001

Data Index: 1511908 (Python Code)

Max Activating Token Index: 446

Text #17

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.9797. Min Act: -0.0000

Data Index: 1392355 (Python Code)

Max Activating Token Index: 54

Text #18

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.6772. Min Act: -0.0001

Data Index: 1597365 (Python Code)

Max Activating Token Index: 718

Text #19

Max Range: 2.1988. Min Range: -2.1988

Max Act: 1.8724. Min Act: -0.0000

Data Index: 1626291 (Python Code)

Max Activating Token Index: 45