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

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

Neuron 523 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1386. Min Act: -0.0001

Data Index: 335760 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1180. Min Act: -0.0001

Data Index: 260184 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1081. Min Act: -0.0001

Data Index: 775571 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1041403 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1044. Min Act: -0.0001

Data Index: 985701 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1091. Min Act: -0.0001

Data Index: 735992 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0977. Min Act: -0.0001

Data Index: 874296 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1043. Min Act: -0.0001

Data Index: 435853 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1005. Min Act: -0.0001

Data Index: 151562 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1157906 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1044. Min Act: -0.0001

Data Index: 584920 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1022. Min Act: -0.0001

Data Index: 101032 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1023. Min Act: -0.0001

Data Index: 179267 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0987. Min Act: -0.0001

Data Index: 109408 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1160396 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1143919 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1085. Min Act: -0.0001

Data Index: 639529 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1009. Min Act: -0.0001

Data Index: 48580 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0971. Min Act: -0.0001

Data Index: 956630 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1577478 (Python Code)

Max Activating Token Index: 941