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

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

Neuron 1538 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: 0.1636. Min Range: -0.1636

Max Act: 0.1636. Min Act: -0.0002

Data Index: 1628399 (Python Code)

Max Activating Token Index: 877

Text #1

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1630577 (Python Code)

Max Activating Token Index: 780

Text #2

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1161360 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1480781 (Python Code)

Max Activating Token Index: 356

Text #4

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1136. Min Act: -0.0002

Data Index: 1573436 (Python Code)

Max Activating Token Index: 383

Text #5

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1540288 (Python Code)

Max Activating Token Index: 690

Text #6

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1038. Min Act: -0.0002

Data Index: 765812 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1345400 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1095. Min Act: -0.0002

Data Index: 1436339 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1041. Min Act: -0.0002

Data Index: 304881 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0995. Min Act: -0.0002

Data Index: 362761 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1024. Min Act: -0.0002

Data Index: 156834 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1647095 (Python Code)

Max Activating Token Index: 544

Text #13

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0990. Min Act: -0.0002

Data Index: 192232 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1608005 (Python Code)

Max Activating Token Index: 427

Text #15

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0963. Min Act: -0.0002

Data Index: 271721 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0963. Min Act: -0.0001

Data Index: 688230 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1006. Min Act: -0.0002

Data Index: 1390388 (Python Code)

Max Activating Token Index: 440

Text #18

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1600236 (Python Code)

Max Activating Token Index: 471

Text #19

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1380412 (Python Code)

Max Activating Token Index: 997