Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 370 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.1991. Min Act: -0.0000

Data Index: 78581 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.1981. Min Act: -0.0000

Data Index: 28952 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.1675. Min Act: -0.0000

Data Index: 303985 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.0671. Min Act: -0.0000

Data Index: 1171297 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1012784 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.1855. Min Act: -0.0000

Data Index: 886327 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.0236. Min Act: -0.0000

Data Index: 1210894 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.1926. Min Act: -0.0000

Data Index: 1129634 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1238168 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1343829 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.0236. Min Act: -0.0000

Data Index: 697679 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1614560 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9689. Min Act: -0.0000

Data Index: 623781 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9757. Min Act: -0.0000

Data Index: 710262 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.0660. Min Act: -0.0000

Data Index: 1003683 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9019. Min Act: -0.0000

Data Index: 1025261 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9055. Min Act: -0.0000

Data Index: 268105 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9001. Min Act: -0.0000

Data Index: 865292 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8964. Min Act: -0.0000

Data Index: 1092675 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9160. Min Act: -0.0000

Data Index: 472783 (C4 (Web Text))

Max Activating Token Index: 389