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

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

Neuron 4205 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0001

Data Index: 72661 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1283. Min Act: -0.0001

Data Index: 22631 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1045580 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1160. Min Act: -0.0001

Data Index: 205439 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1174. Min Act: -0.0001

Data Index: 495238 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1084475 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1159. Min Act: -0.0001

Data Index: 723082 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1073187 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1031. Min Act: -0.0001

Data Index: 174277 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1298704 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0984. Min Act: -0.0001

Data Index: 146708 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1118251 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1049. Min Act: -0.0001

Data Index: 214403 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1350327 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1010. Min Act: -0.0001

Data Index: 651249 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1029543 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0952. Min Act: -0.0001

Data Index: 46941 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0954. Min Act: -0.0001

Data Index: 868606 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1218540 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0949. Min Act: -0.0001

Data Index: 757287 (C4 (Web Text))

Max Activating Token Index: 26