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

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

Neuron 1384 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: 0.1908. Min Range: -0.1908

Max Act: 0.1908. Min Act: -0.0000

Data Index: 976826 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1645. Min Act: -0.0000

Data Index: 218154 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1151037 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1068. Min Act: -0.0000

Data Index: 49698 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1086. Min Act: -0.0000

Data Index: 525445 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1156. Min Act: -0.0000

Data Index: 93812 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1126. Min Act: -0.0000

Data Index: 811815 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1037. Min Act: -0.0000

Data Index: 311700 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1024. Min Act: -0.0000

Data Index: 873411 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1017. Min Act: -0.0000

Data Index: 304813 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1334929 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1069. Min Act: -0.0000

Data Index: 264892 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1110. Min Act: -0.0000

Data Index: 36310 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1205826 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.0852. Min Act: -0.0000

Data Index: 778147 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.0938. Min Act: -0.0000

Data Index: 652952 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.0928. Min Act: -0.0000

Data Index: 602305 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1102. Min Act: -0.0001

Data Index: 73716 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.0960. Min Act: -0.0000

Data Index: 447693 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.0976. Min Act: -0.0000

Data Index: 14432 (C4 (Web Text))

Max Activating Token Index: 236