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

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

Neuron 4929 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: 0.1985. Min Range: -0.1985

Max Act: 0.1985. Min Act: -0.0000

Data Index: 46415 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1526. Min Act: -0.0000

Data Index: 485281 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1418. Min Act: -0.0000

Data Index: 938870 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1320. Min Act: -0.0000

Data Index: 1044051 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1283. Min Act: -0.0000

Data Index: 510929 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1315. Min Act: -0.0000

Data Index: 716858 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1167. Min Act: -0.0000

Data Index: 635539 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1151. Min Act: -0.0000

Data Index: 368488 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1199. Min Act: -0.0000

Data Index: 908455 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1302973 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1150. Min Act: -0.0000

Data Index: 934743 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1093. Min Act: -0.0000

Data Index: 737201 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1241408 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1606245 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1097. Min Act: -0.0000

Data Index: 702365 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1151. Min Act: -0.0000

Data Index: 303548 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1012061 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1020. Min Act: -0.0000

Data Index: 979046 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0914. Min Act: -0.0000

Data Index: 86518 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1167. Min Act: -0.0000

Data Index: 710323 (C4 (Web Text))

Max Activating Token Index: 328