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

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

Neuron 4799 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1547990 (Python Code)

Max Activating Token Index: 473

Text #1

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1377673 (Python Code)

Max Activating Token Index: 337

Text #2

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1381582 (Python Code)

Max Activating Token Index: 706

Text #3

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1410168 (Python Code)

Max Activating Token Index: 747

Text #4

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1472354 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1542540 (Python Code)

Max Activating Token Index: 541

Text #6

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1558523 (Python Code)

Max Activating Token Index: 260

Text #7

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1485514 (Python Code)

Max Activating Token Index: 166

Text #8

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1424523 (Python Code)

Max Activating Token Index: 1016

Text #9

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1403854 (Python Code)

Max Activating Token Index: 844

Text #10

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1572693 (Python Code)

Max Activating Token Index: 182

Text #11

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1560871 (Python Code)

Max Activating Token Index: 74

Text #12

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1378660 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1500328 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1384715 (Python Code)

Max Activating Token Index: 568

Text #15

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1435275 (Python Code)

Max Activating Token Index: 845

Text #16

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1587. Min Act: -0.0000

Data Index: 678346 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1541581 (Python Code)

Max Activating Token Index: 339

Text #18

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1584428 (Python Code)

Max Activating Token Index: 243

Text #19

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1494747 (Python Code)

Max Activating Token Index: 655