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

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

Neuron 6124 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: 1.8200. Min Range: -1.8200

Max Act: 1.8193. Min Act: -0.0002

Data Index: 1628792 (Python Code)

Max Activating Token Index: 781

Text #1

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.8200. Min Act: -0.0002

Data Index: 1436127 (Python Code)

Max Activating Token Index: 847

Text #2

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.7243. Min Act: -0.0002

Data Index: 1380196 (Python Code)

Max Activating Token Index: 609

Text #3

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.7496. Min Act: -0.0002

Data Index: 1637426 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.7640. Min Act: -0.0002

Data Index: 1644011 (Python Code)

Max Activating Token Index: 568

Text #5

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.7400. Min Act: -0.0002

Data Index: 1554049 (Python Code)

Max Activating Token Index: 669

Text #6

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.7495. Min Act: -0.0002

Data Index: 1510889 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.7142. Min Act: -0.0002

Data Index: 1494725 (Python Code)

Max Activating Token Index: 926

Text #8

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.7414. Min Act: -0.0002

Data Index: 1603026 (Python Code)

Max Activating Token Index: 536

Text #9

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.6841. Min Act: -0.0002

Data Index: 1643997 (Python Code)

Max Activating Token Index: 828

Text #10

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.6881. Min Act: -0.0002

Data Index: 1622332 (Python Code)

Max Activating Token Index: 764

Text #11

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.6655. Min Act: -0.0002

Data Index: 1400610 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.6888. Min Act: -0.0002

Data Index: 1388142 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.7270. Min Act: -0.0002

Data Index: 1461631 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.6744. Min Act: -0.0002

Data Index: 1480528 (Python Code)

Max Activating Token Index: 477

Text #15

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.6846. Min Act: -0.0002

Data Index: 1414201 (Python Code)

Max Activating Token Index: 764

Text #16

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.7059. Min Act: -0.0002

Data Index: 1604938 (Python Code)

Max Activating Token Index: 537

Text #17

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.6480. Min Act: -0.0002

Data Index: 1423151 (Python Code)

Max Activating Token Index: 842

Text #18

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.7105. Min Act: -0.0002

Data Index: 1633238 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.6954. Min Act: -0.0002

Data Index: 1595814 (Python Code)

Max Activating Token Index: 607