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

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

Neuron 3711 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: 0.1230. Min Range: -0.1230

Max Act: 0.1204. Min Act: -0.0001

Data Index: 583858 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1230. Min Act: -0.0001

Data Index: 176978 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1209. Min Act: -0.0001

Data Index: 795830 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1206. Min Act: -0.0001

Data Index: 390213 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1091641 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1182. Min Act: -0.0001

Data Index: 262405 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1111. Min Act: -0.0001

Data Index: 18939 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1110. Min Act: -0.0001

Data Index: 899572 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1175. Min Act: -0.0001

Data Index: 507620 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1151. Min Act: -0.0001

Data Index: 434101 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1067. Min Act: -0.0001

Data Index: 781079 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1300088 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1135. Min Act: -0.0001

Data Index: 876479 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1095. Min Act: -0.0001

Data Index: 263661 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1192802 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1072. Min Act: -0.0001

Data Index: 876052 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1241427 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1289031 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1070776 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1240930 (C4 (Web Text))

Max Activating Token Index: 782