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

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

Neuron 348 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1482. Min Act: -0.0000

Data Index: 511754 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1546. Min Act: -0.0000

Data Index: 946823 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1011729 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1269. Min Act: -0.0000

Data Index: 1009326 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1178. Min Act: -0.0000

Data Index: 605544 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1189543 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1274. Min Act: -0.0000

Data Index: 639253 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1068. Min Act: -0.0000

Data Index: 90880 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1057587 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1106. Min Act: -0.0000

Data Index: 985131 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1107. Min Act: -0.0000

Data Index: 4124 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1072. Min Act: -0.0000

Data Index: 465335 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1236636 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0980. Min Act: -0.0000

Data Index: 377031 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0997. Min Act: -0.0000

Data Index: 133520 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1026. Min Act: -0.0000

Data Index: 78871 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1055. Min Act: -0.0000

Data Index: 593325 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1355523 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1054994 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1018. Min Act: -0.0000

Data Index: 84347 (C4 (Web Text))

Max Activating Token Index: 514