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

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

Neuron 1175 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: 0.0812. Min Range: -0.0812

Max Act: 0.0775. Min Act: -0.0002

Data Index: 631030 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0796. Min Act: -0.0002

Data Index: 403135 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0812. Min Act: -0.0002

Data Index: 92025 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0740. Min Act: -0.0002

Data Index: 634123 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1331955 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1315729 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1353327 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1096611 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0688. Min Act: -0.0002

Data Index: 687375 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1193534 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0596. Min Act: -0.0002

Data Index: 777510 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1315087 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0637. Min Act: -0.0002

Data Index: 742419 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0599. Min Act: -0.0002

Data Index: 522355 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1001816 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1025195 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0574. Min Act: -0.0002

Data Index: 970602 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0713. Min Act: -0.0002

Data Index: 498626 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0526. Min Act: -0.0002

Data Index: 286861 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0506. Min Act: -0.0002

Data Index: 506070 (C4 (Web Text))

Max Activating Token Index: 730