Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2860 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2456. Min Act: -0.0004

Data Index: 730909 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1994. Min Act: -0.0004

Data Index: 1219977 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1950. Min Act: -0.0004

Data Index: 17065 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.2003. Min Act: -0.0004

Data Index: 44189 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1974. Min Act: -0.0004

Data Index: 1007584 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1865. Min Act: -0.0004

Data Index: 847075 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1917. Min Act: -0.0004

Data Index: 483179 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1817. Min Act: -0.0004

Data Index: 1147473 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1810. Min Act: -0.0004

Data Index: 570901 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1786. Min Act: -0.0004

Data Index: 807150 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1718. Min Act: -0.0004

Data Index: 818913 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1760. Min Act: -0.0004

Data Index: 1167242 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1796. Min Act: -0.0004

Data Index: 1285978 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1654. Min Act: -0.0004

Data Index: 503204 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1728. Min Act: -0.0004

Data Index: 1087420 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1685. Min Act: -0.0004

Data Index: 138729 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1636. Min Act: -0.0004

Data Index: 419981 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1682. Min Act: -0.0004

Data Index: 891052 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1652. Min Act: -0.0004

Data Index: 205607 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.2456. Min Range: -0.2456

Max Act: 0.1650. Min Act: -0.0004

Data Index: 431337 (C4 (Web Text))

Max Activating Token Index: 13