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

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

Neuron 1315 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1721. Min Range: -3.1721

Max Act: 3.1721. Min Act: -0.0000

Data Index: 145858 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.6693. Min Act: -0.0000

Data Index: 1150371 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.4096. Min Act: -0.0000

Data Index: 44129 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.0743. Min Act: -0.0000

Data Index: 846822 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.1606. Min Act: -0.0000

Data Index: 905165 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.3897. Min Act: -0.0000

Data Index: 192820 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.1710. Min Act: -0.0000

Data Index: 556469 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.0866. Min Act: -0.0000

Data Index: 1115058 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.1734. Min Act: -0.0000

Data Index: 1153824 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.0846. Min Act: -0.0000

Data Index: 547460 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.0678. Min Act: -0.0000

Data Index: 690604 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.0460. Min Act: -0.0000

Data Index: 781771 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 3.1721. Min Range: -3.1721

Max Act: 1.9166. Min Act: -0.0000

Data Index: 44083 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.1126. Min Act: -0.0000

Data Index: 28372 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 3.1721. Min Range: -3.1721

Max Act: 1.9323. Min Act: -0.0000

Data Index: 181936 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 3.1721. Min Range: -3.1721

Max Act: 1.8813. Min Act: -0.0000

Data Index: 1356242 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 3.1721. Min Range: -3.1721

Max Act: 1.9114. Min Act: -0.0000

Data Index: 318478 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 3.1721. Min Range: -3.1721

Max Act: 1.8910. Min Act: -0.0000

Data Index: 513877 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 3.1721. Min Range: -3.1721

Max Act: 1.9720. Min Act: -0.0000

Data Index: 1280766 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 3.1721. Min Range: -3.1721

Max Act: 2.0469. Min Act: -0.0000

Data Index: 929721 (C4 (Web Text))

Max Activating Token Index: 854