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

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

Neuron 512 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: 0.2081. Min Range: -0.2081

Max Act: 0.2081. Min Act: -0.0001

Data Index: 444544 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1803. Min Act: -0.0001

Data Index: 314644 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1660. Min Act: -0.0001

Data Index: 56331 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1680. Min Act: -0.0001

Data Index: 516675 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1743. Min Act: -0.0001

Data Index: 614736 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1346309 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1576. Min Act: -0.0001

Data Index: 785611 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1433. Min Act: -0.0001

Data Index: 554306 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1268870 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1381. Min Act: -0.0001

Data Index: 577856 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1241. Min Act: -0.0001

Data Index: 458782 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1216. Min Act: -0.0001

Data Index: 846928 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1199. Min Act: -0.0001

Data Index: 857444 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1164736 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1158. Min Act: -0.0001

Data Index: 66965 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1073. Min Act: -0.0001

Data Index: 700813 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1015602 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1126. Min Act: -0.0001

Data Index: 715892 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1060. Min Act: -0.0001

Data Index: 85000 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.2081. Min Range: -0.2081

Max Act: 0.1026. Min Act: -0.0001

Data Index: 19083 (C4 (Web Text))

Max Activating Token Index: 749