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

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

Neuron 663 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: 0.1507. Min Range: -0.1507

Max Act: 0.1484. Min Act: -0.0002

Data Index: 1627662 (Python Code)

Max Activating Token Index: 514

Text #1

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1507. Min Act: -0.0002

Data Index: 1628410 (Python Code)

Max Activating Token Index: 197

Text #2

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1426. Min Act: -0.0002

Data Index: 1477621 (Python Code)

Max Activating Token Index: 43

Text #3

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1369. Min Act: -0.0002

Data Index: 1497542 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1648672 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1430482 (Python Code)

Max Activating Token Index: 302

Text #6

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1384073 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1160. Min Act: -0.0002

Data Index: 1634928 (Python Code)

Max Activating Token Index: 784

Text #8

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1487115 (Python Code)

Max Activating Token Index: 158

Text #9

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1472765 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1417734 (Python Code)

Max Activating Token Index: 428

Text #11

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1363973 (Python Code)

Max Activating Token Index: 750

Text #12

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1598779 (Python Code)

Max Activating Token Index: 445

Text #13

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1479096 (Python Code)

Max Activating Token Index: 118

Text #14

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1058. Min Act: -0.0002

Data Index: 1592057 (Python Code)

Max Activating Token Index: 48

Text #15

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0992. Min Act: -0.0002

Data Index: 1564689 (Python Code)

Max Activating Token Index: 642

Text #16

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1504187 (Python Code)

Max Activating Token Index: 669

Text #17

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1058. Min Act: -0.0002

Data Index: 1600107 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1597464 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1570683 (Python Code)

Max Activating Token Index: 65