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

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

Neuron 4998 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: 1.4032. Min Range: -1.4032

Max Act: 1.4032. Min Act: -0.0001

Data Index: 114542 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.2557. Min Act: -0.0001

Data Index: 516193 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.2155. Min Act: -0.0001

Data Index: 854949 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.1601. Min Act: -0.0001

Data Index: 1012014 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.2228. Min Act: -0.0001

Data Index: 622342 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.2054. Min Act: -0.0001

Data Index: 957121 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.0988. Min Act: -0.0001

Data Index: 1199495 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.1363. Min Act: -0.0001

Data Index: 568184 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.0584. Min Act: -0.0001

Data Index: 47922 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.0885. Min Act: -0.0001

Data Index: 317084 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 1.4032. Min Range: -1.4032

Max Act: 0.9653. Min Act: -0.0001

Data Index: 819153 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.0081. Min Act: -0.0001

Data Index: 1273457 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.4032. Min Range: -1.4032

Max Act: 0.9693. Min Act: -0.0001

Data Index: 1224258 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 1.4032. Min Range: -1.4032

Max Act: 0.8915. Min Act: -0.0001

Data Index: 491335 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.0179. Min Act: -0.0001

Data Index: 571940 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 1.4032. Min Range: -1.4032

Max Act: 0.9849. Min Act: -0.0001

Data Index: 558227 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 1.4032. Min Range: -1.4032

Max Act: 0.9751. Min Act: -0.0001

Data Index: 531796 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.0416. Min Act: -0.0001

Data Index: 554740 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 1.4032. Min Range: -1.4032

Max Act: 1.0042. Min Act: -0.0001

Data Index: 504119 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 1.4032. Min Range: -1.4032

Max Act: 0.9961. Min Act: -0.0001

Data Index: 733535 (C4 (Web Text))

Max Activating Token Index: 9