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

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

Neuron 3146 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: 0.0901. Min Range: -0.0901

Max Act: 0.0901. Min Act: -0.0001

Data Index: 667468 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0820. Min Act: -0.0001

Data Index: 167896 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0792. Min Act: -0.0001

Data Index: 653022 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0707. Min Act: -0.0001

Data Index: 604319 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0825. Min Act: -0.0001

Data Index: 152459 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0760. Min Act: -0.0001

Data Index: 650767 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0756. Min Act: -0.0001

Data Index: 728918 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0765. Min Act: -0.0001

Data Index: 297906 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1283774 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0804. Min Act: -0.0001

Data Index: 492772 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0706. Min Act: -0.0001

Data Index: 746444 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0696. Min Act: -0.0001

Data Index: 791196 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0642. Min Act: -0.0001

Data Index: 200075 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1044504 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0706. Min Act: -0.0001

Data Index: 558336 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0684. Min Act: -0.0001

Data Index: 458563 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0638. Min Act: -0.0001

Data Index: 608756 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1185019 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0639. Min Act: -0.0001

Data Index: 222231 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1602723 (Python Code)

Max Activating Token Index: 59