Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1890 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1451. Min Act: -0.0001

Data Index: 50398 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1211. Min Act: -0.0001

Data Index: 420520 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1127. Min Act: -0.0001

Data Index: 735272 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1434. Min Act: -0.0000

Data Index: 793593 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1155. Min Act: -0.0001

Data Index: 887736 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1274. Min Act: -0.0001

Data Index: 492395 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1147. Min Act: -0.0001

Data Index: 967222 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1140. Min Act: -0.0001

Data Index: 253834 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1094. Min Act: -0.0001

Data Index: 314478 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1131887 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1199. Min Act: -0.0001

Data Index: 623647 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1145. Min Act: -0.0000

Data Index: 162851 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1096. Min Act: -0.0001

Data Index: 843945 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1248642 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1095. Min Act: -0.0001

Data Index: 508914 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1091. Min Act: -0.0001

Data Index: 483500 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1129. Min Act: -0.0000

Data Index: 146901 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1063833 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1126243 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1084. Min Act: -0.0000

Data Index: 790885 (C4 (Web Text))

Max Activating Token Index: 136