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

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

Neuron 1194 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.9762. Min Act: -0.0000

Data Index: 373851 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.4725. Min Act: -0.0000

Data Index: 1219913 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.3561. Min Act: -0.0000

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.0775. Min Act: -0.0000

Data Index: 685087 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.2261. Min Act: -0.0000

Data Index: 1573177 (Python Code)

Max Activating Token Index: 166

Text #5

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.1377. Min Act: -0.0000

Data Index: 901922 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.3014. Min Act: -0.0000

Data Index: 1016425 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.2251. Min Act: -0.0000

Data Index: 834064 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.4111. Min Act: -0.0000

Data Index: 393803 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.1582. Min Act: -0.0000

Data Index: 857865 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 5.9762. Min Range: -5.9762

Max Act: 4.7394. Min Act: -0.0000

Data Index: 232880 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.1521. Min Act: -0.0000

Data Index: 309375 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.1555. Min Act: -0.0000

Data Index: 920622 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 5.9762. Min Range: -5.9762

Max Act: 4.9516. Min Act: -0.0000

Data Index: 113695 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.1143. Min Act: -0.0000

Data Index: 722044 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 5.9762. Min Range: -5.9762

Max Act: 4.8970. Min Act: -0.0000

Data Index: 1507633 (Python Code)

Max Activating Token Index: 640

Text #16

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.0951. Min Act: -0.0000

Data Index: 1267258 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 5.9762. Min Range: -5.9762

Max Act: 4.9742. Min Act: -0.0000

Data Index: 890514 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 5.9762. Min Range: -5.9762

Max Act: 4.8218. Min Act: -0.0000

Data Index: 1126814 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 5.9762. Min Range: -5.9762

Max Act: 4.9566. Min Act: -0.0000

Data Index: 895837 (C4 (Web Text))

Max Activating Token Index: 577