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

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

Neuron 3542 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2614. Min Range: -1.2614

Max Act: 1.2614. Min Act: -0.0001

Data Index: 147480 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 1.2614. Min Range: -1.2614

Max Act: 1.0856. Min Act: -0.0001

Data Index: 665820 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 1.2614. Min Range: -1.2614

Max Act: 1.0977. Min Act: -0.0001

Data Index: 638741 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.2614. Min Range: -1.2614

Max Act: 1.0551. Min Act: -0.0001

Data Index: 288014 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9351. Min Act: -0.0000

Data Index: 1424349 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9542. Min Act: -0.0001

Data Index: 1471817 (Python Code)

Max Activating Token Index: 610

Text #6

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9753. Min Act: -0.0001

Data Index: 110821 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1385344 (Python Code)

Max Activating Token Index: 475

Text #8

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9291. Min Act: -0.0001

Data Index: 1559512 (Python Code)

Max Activating Token Index: 285

Text #9

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.8879. Min Act: -0.0001

Data Index: 1477740 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.8683. Min Act: -0.0001

Data Index: 1378298 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9270. Min Act: -0.0001

Data Index: 1627757 (Python Code)

Max Activating Token Index: 705

Text #12

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.7146. Min Act: -0.0001

Data Index: 1162850 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.8753. Min Act: -0.0001

Data Index: 890006 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9389. Min Act: -0.0000

Data Index: 1593298 (Python Code)

Max Activating Token Index: 549

Text #15

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1448280 (Python Code)

Max Activating Token Index: 700

Text #16

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.8499. Min Act: -0.0001

Data Index: 962481 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.8684. Min Act: -0.0001

Data Index: 1608554 (Python Code)

Max Activating Token Index: 1022

Text #18

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1176323 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1426881 (Python Code)

Max Activating Token Index: 737