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

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

Neuron 434 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: 0.2179. Min Range: -0.2179

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1614956 (Python Code)

Max Activating Token Index: 266

Text #1

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.2179. Min Act: -0.0001

Data Index: 272813 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1981. Min Act: -0.0000

Data Index: 701555 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1436205 (Python Code)

Max Activating Token Index: 735

Text #4

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1937. Min Act: -0.0000

Data Index: 472789 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1068874 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1964. Min Act: -0.0001

Data Index: 773247 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1883. Min Act: -0.0001

Data Index: 687310 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1868. Min Act: -0.0001

Data Index: 1261173 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1878. Min Act: -0.0001

Data Index: 446461 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1861. Min Act: -0.0000

Data Index: 712232 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1774. Min Act: -0.0001

Data Index: 509636 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1871. Min Act: -0.0001

Data Index: 26976 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1559067 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1769. Min Act: -0.0001

Data Index: 1160604 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1784. Min Act: -0.0001

Data Index: 1132922 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1760. Min Act: -0.0001

Data Index: 1070405 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1855. Min Act: -0.0001

Data Index: 714903 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1790. Min Act: -0.0001

Data Index: 365900 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1734. Min Act: -0.0000

Data Index: 17098 (C4 (Web Text))

Max Activating Token Index: 417