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

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

Neuron 3312 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.9634. Min Act: -0.0002

Data Index: 1502242 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.9095. Min Act: -0.0002

Data Index: 1417250 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.9065. Min Act: -0.0002

Data Index: 1378262 (Python Code)

Max Activating Token Index: 331

Text #3

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8813. Min Act: -0.0002

Data Index: 1558463 (Python Code)

Max Activating Token Index: 110

Text #4

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8917. Min Act: -0.0002

Data Index: 1448880 (Python Code)

Max Activating Token Index: 264

Text #5

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8882. Min Act: -0.0002

Data Index: 1458723 (Python Code)

Max Activating Token Index: 32

Text #6

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8746. Min Act: -0.0002

Data Index: 1617666 (Python Code)

Max Activating Token Index: 777

Text #7

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8453. Min Act: -0.0002

Data Index: 1464465 (Python Code)

Max Activating Token Index: 329

Text #8

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8591. Min Act: -0.0002

Data Index: 1655243 (Python Code)

Max Activating Token Index: 974

Text #9

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8583. Min Act: -0.0002

Data Index: 1564303 (Python Code)

Max Activating Token Index: 543

Text #10

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8432. Min Act: -0.0002

Data Index: 1478677 (Python Code)

Max Activating Token Index: 976

Text #11

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8448. Min Act: -0.0002

Data Index: 1382868 (Python Code)

Max Activating Token Index: 947

Text #12

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8476. Min Act: -0.0002

Data Index: 1565872 (Python Code)

Max Activating Token Index: 823

Text #13

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8289. Min Act: -0.0002

Data Index: 1618122 (Python Code)

Max Activating Token Index: 340

Text #14

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8274. Min Act: -0.0002

Data Index: 1473389 (Python Code)

Max Activating Token Index: 605

Text #15

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8348. Min Act: -0.0002

Data Index: 1520651 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8232. Min Act: -0.0002

Data Index: 13990 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8404. Min Act: -0.0002

Data Index: 1558286 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8111. Min Act: -0.0002

Data Index: 1401537 (Python Code)

Max Activating Token Index: 848

Text #19

Max Range: 0.9634. Min Range: -0.9634

Max Act: 0.8174. Min Act: -0.0002

Data Index: 1565491 (Python Code)

Max Activating Token Index: 608