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

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

Neuron 4338 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: 0.1285. Min Range: -0.1285

Max Act: 0.1285. Min Act: -0.0001

Data Index: 888391 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1305711 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1212. Min Act: -0.0001

Data Index: 37182 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1166. Min Act: -0.0001

Data Index: 797101 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1152. Min Act: -0.0001

Data Index: 747298 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1247189 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1052729 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1140385 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1076. Min Act: -0.0001

Data Index: 84308 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1030. Min Act: -0.0001

Data Index: 788683 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1144922 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1558398 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0961. Min Act: -0.0001

Data Index: 550970 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1045080 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0798. Min Act: -0.0001

Data Index: 134102 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1030434 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1014577 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1157201 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0920. Min Act: -0.0001

Data Index: 44457 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0889. Min Act: -0.0001

Data Index: 834156 (C4 (Web Text))

Max Activating Token Index: 951