Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3165 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2774. Min Act: -0.0001

Data Index: 518796 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2500. Min Act: -0.0001

Data Index: 734631 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2419. Min Act: -0.0001

Data Index: 293755 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1213005 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2125. Min Act: -0.0000

Data Index: 519281 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2050. Min Act: -0.0001

Data Index: 482362 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2089. Min Act: -0.0001

Data Index: 833865 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2044. Min Act: -0.0001

Data Index: 953681 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.1955. Min Act: -0.0000

Data Index: 486155 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.1977. Min Act: -0.0001

Data Index: 252684 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.1977. Min Act: -0.0000

Data Index: 310154 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1109889 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.1861. Min Act: -0.0001

Data Index: 283807 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.1870. Min Act: -0.0001

Data Index: 1210311 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.1943. Min Act: -0.0000

Data Index: 15 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.1988. Min Act: -0.0001

Data Index: 364381 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.1873. Min Act: -0.0001

Data Index: 142696 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2006. Min Act: -0.0001

Data Index: 203850 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.1788. Min Act: -0.0001

Data Index: 800495 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.1862. Min Act: -0.0000

Data Index: 965763 (C4 (Web Text))

Max Activating Token Index: 903