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

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

Neuron 5044 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.8415. Min Act: -0.0002

Data Index: 1644771 (Python Code)

Max Activating Token Index: 735

Text #1

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.7978. Min Act: -0.0002

Data Index: 1499561 (Python Code)

Max Activating Token Index: 248

Text #2

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.8771. Min Act: -0.0002

Data Index: 1573678 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.8771. Min Act: -0.0002

Data Index: 1626352 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.8771. Min Act: -0.0002

Data Index: 1635067 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.8771. Min Act: -0.0002

Data Index: 1403774 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.7611. Min Act: -0.0002

Data Index: 1489670 (Python Code)

Max Activating Token Index: 113

Text #7

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.6750. Min Act: -0.0002

Data Index: 1463714 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.6609. Min Act: -0.0002

Data Index: 1371552 (Python Code)

Max Activating Token Index: 354

Text #9

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.5626. Min Act: -0.0002

Data Index: 1460978 (Python Code)

Max Activating Token Index: 122

Text #10

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.6922. Min Act: -0.0002

Data Index: 1378078 (Python Code)

Max Activating Token Index: 365

Text #11

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.5224. Min Act: -0.0002

Data Index: 1570688 (Python Code)

Max Activating Token Index: 184

Text #12

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.6080. Min Act: -0.0002

Data Index: 1558971 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.8282. Min Act: -0.0002

Data Index: 1394847 (Python Code)

Max Activating Token Index: 993

Text #14

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.6847. Min Act: -0.0002

Data Index: 1460601 (Python Code)

Max Activating Token Index: 903

Text #15

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.5383. Min Act: -0.0002

Data Index: 1580296 (Python Code)

Max Activating Token Index: 163

Text #16

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.4928. Min Act: -0.0002

Data Index: 1607446 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.3681. Min Act: -0.0002

Data Index: 1447778 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.6913. Min Act: -0.0002

Data Index: 1530571 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.5538. Min Act: -0.0002

Data Index: 1521407 (Python Code)

Max Activating Token Index: 46