Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1527 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1509. Min Act: -0.0002

Data Index: 1475001 (Python Code)

Max Activating Token Index: 908

Text #1

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1499. Min Act: -0.0002

Data Index: 1481471 (Python Code)

Max Activating Token Index: 612

Text #2

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1277. Min Act: -0.0002

Data Index: 1585447 (Python Code)

Max Activating Token Index: 993

Text #3

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1262. Min Act: -0.0002

Data Index: 1576349 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1553351 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1328. Min Act: -0.0002

Data Index: 1558595 (Python Code)

Max Activating Token Index: 311

Text #6

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1200. Min Act: -0.0002

Data Index: 1366585 (Python Code)

Max Activating Token Index: 764

Text #7

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1178. Min Act: -0.0002

Data Index: 1584519 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1118. Min Act: -0.0002

Data Index: 1562152 (Python Code)

Max Activating Token Index: 269

Text #9

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1482608 (Python Code)

Max Activating Token Index: 702

Text #10

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1186. Min Act: -0.0002

Data Index: 1502700 (Python Code)

Max Activating Token Index: 652

Text #11

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1194. Min Act: -0.0002

Data Index: 1462197 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1417925 (Python Code)

Max Activating Token Index: 781

Text #13

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1101. Min Act: -0.0002

Data Index: 1420949 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1035. Min Act: -0.0002

Data Index: 1618393 (Python Code)

Max Activating Token Index: 340

Text #15

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1073. Min Act: -0.0002

Data Index: 1543968 (Python Code)

Max Activating Token Index: 880

Text #16

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1524072 (Python Code)

Max Activating Token Index: 1005

Text #17

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1403088 (Python Code)

Max Activating Token Index: 575

Text #18

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1387489 (Python Code)

Max Activating Token Index: 637

Text #19

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1641065 (Python Code)

Max Activating Token Index: 297