Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 64 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0751. Min Range: -2.0751

Max Act: 2.0751. Min Act: -0.0000

Data Index: 1595306 (Python Code)

Max Activating Token Index: 136

Text #1

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.9527. Min Act: -0.0000

Data Index: 1588227 (Python Code)

Max Activating Token Index: 753

Text #2

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.8902. Min Act: -0.0000

Data Index: 1532524 (Python Code)

Max Activating Token Index: 152

Text #3

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.8833. Min Act: -0.0000

Data Index: 1456716 (Python Code)

Max Activating Token Index: 853

Text #4

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.7561. Min Act: -0.0000

Data Index: 1368421 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.8024. Min Act: -0.0000

Data Index: 1385932 (Python Code)

Max Activating Token Index: 730

Text #6

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.6909. Min Act: -0.0000

Data Index: 1637712 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.6725. Min Act: -0.0000

Data Index: 1601863 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.5299. Min Act: -0.0000

Data Index: 1471682 (Python Code)

Max Activating Token Index: 594

Text #9

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.5156. Min Act: -0.0000

Data Index: 1559869 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.6105. Min Act: -0.0000

Data Index: 1429449 (Python Code)

Max Activating Token Index: 396

Text #11

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.5124. Min Act: -0.0000

Data Index: 1465228 (Python Code)

Max Activating Token Index: 795

Text #12

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.6678. Min Act: -0.0000

Data Index: 1522413 (Python Code)

Max Activating Token Index: 742

Text #13

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.5793. Min Act: -0.0000

Data Index: 1386083 (Python Code)

Max Activating Token Index: 363

Text #14

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.5631. Min Act: -0.0000

Data Index: 1492878 (Python Code)

Max Activating Token Index: 182

Text #15

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.6129. Min Act: -0.0000

Data Index: 1566493 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.4563. Min Act: -0.0000

Data Index: 1377731 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.5529. Min Act: -0.0000

Data Index: 1486579 (Python Code)

Max Activating Token Index: 988

Text #18

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.4390. Min Act: -0.0000

Data Index: 1431302 (Python Code)

Max Activating Token Index: 180

Text #19

Max Range: 2.0751. Min Range: -2.0751

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1371041 (Python Code)

Max Activating Token Index: 329