Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 16 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1247. Min Act: -0.0005

Data Index: 946609 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1094. Min Act: -0.0005

Data Index: 337863 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1179. Min Act: -0.0004

Data Index: 340425 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1141. Min Act: -0.0005

Data Index: 26831 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1055. Min Act: -0.0005

Data Index: 905975 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1075. Min Act: -0.0005

Data Index: 376349 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1037. Min Act: -0.0005

Data Index: 214568 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1114. Min Act: -0.0005

Data Index: 1294510 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1054. Min Act: -0.0005

Data Index: 202598 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1035. Min Act: -0.0005

Data Index: 248059 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1046. Min Act: -0.0005

Data Index: 916650 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0987. Min Act: -0.0005

Data Index: 276446 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.1016. Min Act: -0.0005

Data Index: 759340 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0965. Min Act: -0.0005

Data Index: 823862 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0933. Min Act: -0.0005

Data Index: 1244471 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0968. Min Act: -0.0005

Data Index: 131861 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0967. Min Act: -0.0005

Data Index: 955265 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0964. Min Act: -0.0005

Data Index: 626456 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0911. Min Act: -0.0005

Data Index: 292536 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.1247. Min Range: -0.1247

Max Act: 0.0974. Min Act: -0.0005

Data Index: 1306557 (C4 (Web Text))

Max Activating Token Index: 989