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

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

Neuron 1734 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0002

Data Index: 971280 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1376. Min Act: -0.0002

Data Index: 123234 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1320. Min Act: -0.0002

Data Index: 597505 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1171. Min Act: -0.0002

Data Index: 688580 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1175. Min Act: -0.0002

Data Index: 650728 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1176. Min Act: -0.0002

Data Index: 893604 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1247910 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1064. Min Act: -0.0002

Data Index: 792697 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1124. Min Act: -0.0002

Data Index: 1115254 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1056. Min Act: -0.0002

Data Index: 282265 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1099. Min Act: -0.0002

Data Index: 546637 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0970. Min Act: -0.0002

Data Index: 770953 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1035. Min Act: -0.0002

Data Index: 18125 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1022. Min Act: -0.0002

Data Index: 329883 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1268525 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1002. Min Act: -0.0002

Data Index: 261364 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0919. Min Act: -0.0002

Data Index: 353453 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0990. Min Act: -0.0002

Data Index: 278942 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1009. Min Act: -0.0002

Data Index: 310414 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1243036 (C4 (Web Text))

Max Activating Token Index: 327