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

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

Neuron 2663 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1373. Min Act: -0.0001

Data Index: 870857 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1309. Min Act: -0.0001

Data Index: 936892 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1239580 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1310. Min Act: -0.0001

Data Index: 891628 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1215426 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1316238 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1086. Min Act: -0.0001

Data Index: 781876 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1018820 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1092. Min Act: -0.0001

Data Index: 978680 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1677 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1123. Min Act: -0.0001

Data Index: 344931 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0990. Min Act: -0.0001

Data Index: 716233 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1017. Min Act: -0.0001

Data Index: 8118 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1007. Min Act: -0.0001

Data Index: 205578 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0959. Min Act: -0.0001

Data Index: 12880 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0955. Min Act: -0.0001

Data Index: 805059 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0782. Min Act: -0.0001

Data Index: 34114 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0991. Min Act: -0.0001

Data Index: 17135 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0983. Min Act: -0.0001

Data Index: 912492 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1280368 (C4 (Web Text))

Max Activating Token Index: 552