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

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

Neuron 1173 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1067418 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1347788 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1154. Min Act: -0.0001

Data Index: 177689 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1357182 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1087. Min Act: -0.0001

Data Index: 807039 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1073. Min Act: -0.0001

Data Index: 266874 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1228661 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1060. Min Act: -0.0001

Data Index: 100227 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0968. Min Act: -0.0001

Data Index: 176272 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1013. Min Act: -0.0001

Data Index: 714341 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1015762 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0999. Min Act: -0.0001

Data Index: 912652 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0997. Min Act: -0.0001

Data Index: 635779 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1097. Min Act: -0.0001

Data Index: 888641 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0950. Min Act: -0.0001

Data Index: 636101 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0976. Min Act: -0.0001

Data Index: 464616 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1223405 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0931. Min Act: -0.0001

Data Index: 787953 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0956. Min Act: -0.0001

Data Index: 89045 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1081641 (C4 (Web Text))

Max Activating Token Index: 158