Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1992 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1622. Min Act: -0.0003

Data Index: 1426182 (Python Code)

Max Activating Token Index: 350

Text #1

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1345. Min Act: -0.0003

Data Index: 1586860 (Python Code)

Max Activating Token Index: 211

Text #2

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1303. Min Act: -0.0003

Data Index: 1504595 (Python Code)

Max Activating Token Index: 500

Text #3

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1273. Min Act: -0.0003

Data Index: 1595659 (Python Code)

Max Activating Token Index: 228

Text #4

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1208. Min Act: -0.0003

Data Index: 1443361 (Python Code)

Max Activating Token Index: 340

Text #5

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1103. Min Act: -0.0003

Data Index: 1424129 (Python Code)

Max Activating Token Index: 160

Text #6

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1134. Min Act: -0.0003

Data Index: 1613338 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1071. Min Act: -0.0003

Data Index: 1446704 (Python Code)

Max Activating Token Index: 688

Text #8

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1062. Min Act: -0.0003

Data Index: 1508619 (Python Code)

Max Activating Token Index: 868

Text #9

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1117. Min Act: -0.0003

Data Index: 1641295 (Python Code)

Max Activating Token Index: 461

Text #10

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1117. Min Act: -0.0003

Data Index: 1421320 (Python Code)

Max Activating Token Index: 462

Text #11

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1072. Min Act: -0.0003

Data Index: 1437004 (Python Code)

Max Activating Token Index: 389

Text #12

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1087. Min Act: -0.0003

Data Index: 1496992 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1067. Min Act: -0.0003

Data Index: 1563199 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1082. Min Act: -0.0003

Data Index: 1493661 (Python Code)

Max Activating Token Index: 415

Text #15

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1074. Min Act: -0.0003

Data Index: 1488748 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1038. Min Act: -0.0003

Data Index: 1512495 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1050. Min Act: -0.0003

Data Index: 1599526 (Python Code)

Max Activating Token Index: 138

Text #18

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1059. Min Act: -0.0003

Data Index: 1574863 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1044. Min Act: -0.0003

Data Index: 1394514 (Python Code)

Max Activating Token Index: 320