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

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

Neuron 1673 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1469. Min Act: -0.0003

Data Index: 713935 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1294. Min Act: -0.0003

Data Index: 1121741 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1096. Min Act: -0.0003

Data Index: 1110342 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1015. Min Act: -0.0003

Data Index: 1205442 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1124. Min Act: -0.0003

Data Index: 1161174 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1121. Min Act: -0.0003

Data Index: 274795 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1063. Min Act: -0.0003

Data Index: 448492 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0907. Min Act: -0.0003

Data Index: 119971 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0998. Min Act: -0.0003

Data Index: 1336103 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1103. Min Act: -0.0003

Data Index: 495014 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0889. Min Act: -0.0003

Data Index: 783755 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1016. Min Act: -0.0003

Data Index: 65984 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0873. Min Act: -0.0003

Data Index: 1278100 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0941. Min Act: -0.0003

Data Index: 674299 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0818. Min Act: -0.0003

Data Index: 1232857 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0947. Min Act: -0.0003

Data Index: 648291 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0959. Min Act: -0.0003

Data Index: 628327 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0770. Min Act: -0.0003

Data Index: 625991 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0859. Min Act: -0.0003

Data Index: 455931 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0851. Min Act: -0.0003

Data Index: 1032229 (C4 (Web Text))

Max Activating Token Index: 462