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

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

Neuron 4617 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.2210. Min Act: -0.0000

Data Index: 603977 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.2112. Min Act: -0.0000

Data Index: 947095 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1962. Min Act: -0.0000

Data Index: 360245 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1869. Min Act: -0.0000

Data Index: 280929 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1919. Min Act: -0.0000

Data Index: 407479 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1805. Min Act: -0.0000

Data Index: 152381 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1869. Min Act: -0.0000

Data Index: 583175 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1927. Min Act: -0.0000

Data Index: 152925 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1152866 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1063099 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1790. Min Act: -0.0000

Data Index: 951933 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1843. Min Act: -0.0000

Data Index: 880596 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1778. Min Act: -0.0000

Data Index: 951030 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1734. Min Act: -0.0000

Data Index: 676830 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1742. Min Act: -0.0000

Data Index: 715232 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1729. Min Act: -0.0000

Data Index: 832430 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1611. Min Act: -0.0000

Data Index: 959241 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1825. Min Act: -0.0000

Data Index: 711971 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1757. Min Act: -0.0000

Data Index: 678281 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1721. Min Act: -0.0000

Data Index: 431751 (C4 (Web Text))

Max Activating Token Index: 253