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

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

Neuron 3443 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.1533. Min Act: -0.0001

Data Index: 1362866 (Python Code)

Max Activating Token Index: 658

Text #1

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.0952. Min Act: -0.0001

Data Index: 1379623 (Python Code)

Max Activating Token Index: 288

Text #2

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.0782. Min Act: -0.0001

Data Index: 1529119 (Python Code)

Max Activating Token Index: 489

Text #3

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.0487. Min Act: -0.0001

Data Index: 1601539 (Python Code)

Max Activating Token Index: 422

Text #4

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.1056. Min Act: -0.0001

Data Index: 1519353 (Python Code)

Max Activating Token Index: 641

Text #5

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.0883. Min Act: -0.0001

Data Index: 1426306 (Python Code)

Max Activating Token Index: 843

Text #6

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1471573 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.0060. Min Act: -0.0001

Data Index: 1541973 (Python Code)

Max Activating Token Index: 524

Text #8

Max Range: 1.1533. Min Range: -1.1533

Max Act: 0.9926. Min Act: -0.0001

Data Index: 1411511 (Python Code)

Max Activating Token Index: 726

Text #9

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.0523. Min Act: -0.0001

Data Index: 1484011 (Python Code)

Max Activating Token Index: 475

Text #10

Max Range: 1.1533. Min Range: -1.1533

Max Act: 0.9881. Min Act: -0.0001

Data Index: 1480327 (Python Code)

Max Activating Token Index: 695

Text #11

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.0451. Min Act: -0.0001

Data Index: 1591861 (Python Code)

Max Activating Token Index: 610

Text #12

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.0431. Min Act: -0.0001

Data Index: 1449698 (Python Code)

Max Activating Token Index: 463

Text #13

Max Range: 1.1533. Min Range: -1.1533

Max Act: 1.0042. Min Act: -0.0001

Data Index: 1480200 (Python Code)

Max Activating Token Index: 282

Text #14

Max Range: 1.1533. Min Range: -1.1533

Max Act: 0.9953. Min Act: -0.0001

Data Index: 1580724 (Python Code)

Max Activating Token Index: 660

Text #15

Max Range: 1.1533. Min Range: -1.1533

Max Act: 0.9444. Min Act: -0.0001

Data Index: 1383955 (Python Code)

Max Activating Token Index: 824

Text #16

Max Range: 1.1533. Min Range: -1.1533

Max Act: 0.9678. Min Act: -0.0001

Data Index: 1592828 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 1.1533. Min Range: -1.1533

Max Act: 0.9813. Min Act: -0.0001

Data Index: 1613538 (Python Code)

Max Activating Token Index: 608

Text #18

Max Range: 1.1533. Min Range: -1.1533

Max Act: 0.9939. Min Act: -0.0001

Data Index: 1441064 (Python Code)

Max Activating Token Index: 397

Text #19

Max Range: 1.1533. Min Range: -1.1533

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1403237 (Python Code)

Max Activating Token Index: 634