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

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

Neuron 1785 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1754. Min Range: -3.1754

Max Act: 3.1754. Min Act: -0.0000

Data Index: 1339097 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 3.1754. Min Range: -3.1754

Max Act: 2.3671. Min Act: -0.0000

Data Index: 1075535 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 3.1754. Min Range: -3.1754

Max Act: 2.1117. Min Act: -0.0000

Data Index: 781450 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.9760. Min Act: -0.0000

Data Index: 68978 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.8651. Min Act: -0.0000

Data Index: 83942 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.8381. Min Act: -0.0000

Data Index: 756871 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.8021. Min Act: -0.0000

Data Index: 1376828 (Python Code)

Max Activating Token Index: 967

Text #7

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.6569. Min Act: 0.0000

Data Index: 423112 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.7331. Min Act: -0.0000

Data Index: 914590 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.6487. Min Act: -0.0000

Data Index: 89354 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.6234. Min Act: -0.0000

Data Index: 833675 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.5852. Min Act: -0.0000

Data Index: 88319 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.5136. Min Act: -0.0000

Data Index: 988915 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.5853. Min Act: -0.0000

Data Index: 313786 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.5579. Min Act: -0.0000

Data Index: 332186 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.4275. Min Act: -0.0000

Data Index: 873782 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.5192. Min Act: -0.0000

Data Index: 886532 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.3811. Min Act: -0.0000

Data Index: 778272 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.2757. Min Act: -0.0000

Data Index: 34752 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 3.1754. Min Range: -3.1754

Max Act: 1.3346. Min Act: -0.0000

Data Index: 241250 (C4 (Web Text))

Max Activating Token Index: 45