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

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

Neuron 1647 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.6639. Min Act: -0.0000

Data Index: 1362994 (Python Code)

Max Activating Token Index: 378

Text #1

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.9708. Min Act: -0.0000

Data Index: 1450101 (Python Code)

Max Activating Token Index: 763

Text #2

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.8270. Min Act: -0.0000

Data Index: 1380131 (Python Code)

Max Activating Token Index: 810

Text #3

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.9899. Min Act: -0.0000

Data Index: 1500290 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.8032. Min Act: -0.0000

Data Index: 1500896 (Python Code)

Max Activating Token Index: 714

Text #5

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.5111. Min Act: -0.0000

Data Index: 1446702 (Python Code)

Max Activating Token Index: 479

Text #6

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.6414. Min Act: -0.0000

Data Index: 1591554 (Python Code)

Max Activating Token Index: 521

Text #7

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.6480. Min Act: -0.0000

Data Index: 1456386 (Python Code)

Max Activating Token Index: 970

Text #8

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.3952. Min Act: -0.0000

Data Index: 1652624 (Python Code)

Max Activating Token Index: 654

Text #9

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.0494. Min Act: -0.0000

Data Index: 1429448 (Python Code)

Max Activating Token Index: 656

Text #10

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.2897. Min Act: -0.0000

Data Index: 1378276 (Python Code)

Max Activating Token Index: 666

Text #11

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.2820. Min Act: -0.0000

Data Index: 1471261 (Python Code)

Max Activating Token Index: 725

Text #12

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.2809. Min Act: -0.0000

Data Index: 1644814 (Python Code)

Max Activating Token Index: 456

Text #13

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.5788. Min Act: -0.0000

Data Index: 1590638 (Python Code)

Max Activating Token Index: 892

Text #14

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.3834. Min Act: -0.0000

Data Index: 1370657 (Python Code)

Max Activating Token Index: 947

Text #15

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.2102. Min Act: -0.0000

Data Index: 1631646 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.3246. Min Act: -0.0000

Data Index: 1590238 (Python Code)

Max Activating Token Index: 906

Text #17

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.1590. Min Act: -0.0000

Data Index: 1384346 (Python Code)

Max Activating Token Index: 154

Text #18

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.0144. Min Act: -0.0000

Data Index: 1421723 (Python Code)

Max Activating Token Index: 773

Text #19

Max Range: 4.6639. Min Range: -4.6639

Max Act: 3.3100. Min Act: -0.0000

Data Index: 1368998 (Python Code)

Max Activating Token Index: 1008