Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3891 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1466673 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1619553 (Python Code)

Max Activating Token Index: 734

Text #2

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1471360 (Python Code)

Max Activating Token Index: 992

Text #3

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1457811 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1463359 (Python Code)

Max Activating Token Index: 724

Text #5

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1462257 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1401217 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4883. Min Act: -0.0000

Data Index: 1401308 (Python Code)

Max Activating Token Index: 788

Text #8

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1645586 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1398835 (Python Code)

Max Activating Token Index: 141

Text #10

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1501070 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1544301 (Python Code)

Max Activating Token Index: 248

Text #12

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1532687 (Python Code)

Max Activating Token Index: 501

Text #13

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1407012 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1517844 (Python Code)

Max Activating Token Index: 483

Text #15

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1616796 (Python Code)

Max Activating Token Index: 595

Text #16

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1434542 (Python Code)

Max Activating Token Index: 876

Text #17

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1604941 (Python Code)

Max Activating Token Index: 416

Text #18

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1649982 (Python Code)

Max Activating Token Index: 249

Text #19

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1549556 (Python Code)

Max Activating Token Index: 550