Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2170 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0840. Min Act: -0.0001

Data Index: 750424 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0807. Min Act: -0.0001

Data Index: 576782 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0853. Min Act: -0.0001

Data Index: 64384 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0843. Min Act: -0.0002

Data Index: 946606 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1244721 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0839. Min Act: -0.0001

Data Index: 627217 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0002

Data Index: 618820 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0823. Min Act: -0.0002

Data Index: 530303 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0825. Min Act: -0.0002

Data Index: 702431 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1168717 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0789. Min Act: -0.0001

Data Index: 708585 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0728. Min Act: -0.0002

Data Index: 522969 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0728. Min Act: -0.0001

Data Index: 884589 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1336195 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0709. Min Act: -0.0002

Data Index: 504759 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0775. Min Act: -0.0002

Data Index: 679049 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0641. Min Act: -0.0001

Data Index: 732615 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0741. Min Act: -0.0001

Data Index: 575434 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0795. Min Act: -0.0001

Data Index: 823780 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0785. Min Act: -0.0002

Data Index: 793423 (C4 (Web Text))

Max Activating Token Index: 897