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

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

Neuron 1856 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1471365 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1600189 (Python Code)

Max Activating Token Index: 620

Text #2

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1565106 (Python Code)

Max Activating Token Index: 670

Text #3

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1511385 (Python Code)

Max Activating Token Index: 821

Text #4

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1373641 (Python Code)

Max Activating Token Index: 532

Text #5

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1589892 (Python Code)

Max Activating Token Index: 685

Text #6

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1620592 (Python Code)

Max Activating Token Index: 819

Text #7

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1510675 (Python Code)

Max Activating Token Index: 919

Text #8

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1592170 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1392525 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1444870 (Python Code)

Max Activating Token Index: 700

Text #11

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1600867 (Python Code)

Max Activating Token Index: 555

Text #12

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1535236 (Python Code)

Max Activating Token Index: 836

Text #13

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1432877 (Python Code)

Max Activating Token Index: 855

Text #14

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1060. Min Act: -0.0001

Data Index: 86093 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1471965 (Python Code)

Max Activating Token Index: 616

Text #16

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1475216 (Python Code)

Max Activating Token Index: 616

Text #17

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1426953 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1480421 (Python Code)

Max Activating Token Index: 974

Text #19

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1489070 (Python Code)

Max Activating Token Index: 735