Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5514 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1287938 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0818. Min Act: -0.0001

Data Index: 972506 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1373155 (Python Code)

Max Activating Token Index: 321

Text #3

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1402602 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1521876 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0766. Min Act: -0.0001

Data Index: 78679 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1143162 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1434355 (Python Code)

Max Activating Token Index: 319

Text #8

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0761. Min Act: -0.0001

Data Index: 392315 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1022000 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1495639 (Python Code)

Max Activating Token Index: 152

Text #11

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0735. Min Act: -0.0001

Data Index: 605455 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0720. Min Act: -0.0001

Data Index: 779871 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1531111 (Python Code)

Max Activating Token Index: 158

Text #14

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0760. Min Act: -0.0001

Data Index: 199558 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0760. Min Act: -0.0001

Data Index: 597508 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1156275 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0724. Min Act: -0.0001

Data Index: 802503 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0702. Min Act: -0.0001

Data Index: 624557 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1058717 (C4 (Web Text))

Max Activating Token Index: 843