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

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

Neuron 2878 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1168022 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1015123 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1332501 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0788. Min Act: -0.0001

Data Index: 691985 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0668. Min Act: -0.0001

Data Index: 140873 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0627. Min Act: -0.0001

Data Index: 422607 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0674. Min Act: -0.0001

Data Index: 771687 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1338747 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0644. Min Act: -0.0001

Data Index: 148770 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0693. Min Act: -0.0001

Data Index: 118633 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1240080 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0599. Min Act: -0.0001

Data Index: 859301 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0578. Min Act: -0.0001

Data Index: 302384 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0596. Min Act: -0.0001

Data Index: 910854 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0684. Min Act: -0.0001

Data Index: 339222 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0599. Min Act: -0.0001

Data Index: 756480 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0607. Min Act: -0.0001

Data Index: 439641 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1096485 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0599. Min Act: -0.0001

Data Index: 843992 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1568863 (Python Code)

Max Activating Token Index: 173