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

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

Neuron 1474 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1086908 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1373. Min Act: -0.0001

Data Index: 800486 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1152415 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1184. Min Act: -0.0001

Data Index: 906048 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1093. Min Act: -0.0001

Data Index: 860823 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1138. Min Act: -0.0001

Data Index: 898231 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1364726 (Python Code)

Max Activating Token Index: 257

Text #7

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1174380 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1052. Min Act: -0.0001

Data Index: 422308 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1016. Min Act: -0.0001

Data Index: 460448 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1089. Min Act: -0.0001

Data Index: 18624 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1023891 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1009. Min Act: -0.0001

Data Index: 871242 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1448675 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1355825 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1000. Min Act: -0.0001

Data Index: 125719 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1119661 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1021. Min Act: -0.0001

Data Index: 302162 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1056. Min Act: -0.0001

Data Index: 795205 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1200187 (C4 (Web Text))

Max Activating Token Index: 958