Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1741 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0763. Min Act: -0.0000

Data Index: 147072 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0770. Min Act: 0.0000

Data Index: 894906 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0763. Min Act: -0.0001

Data Index: 543055 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0613. Min Act: -0.0000

Data Index: 531136 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1332614 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0700. Min Act: -0.0000

Data Index: 50481 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0699. Min Act: 0.0000

Data Index: 395854 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0686. Min Act: -0.0000

Data Index: 989368 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0662. Min Act: -0.0001

Data Index: 263608 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1108851 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1415940 (Python Code)

Max Activating Token Index: 223

Text #11

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0652. Min Act: 0.0000

Data Index: 1632210 (Python Code)

Max Activating Token Index: 143

Text #12

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1004350 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1192982 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0618. Min Act: 0.0000

Data Index: 1054426 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1269714 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0613. Min Act: 0.0000

Data Index: 879937 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1104727 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0608. Min Act: -0.0000

Data Index: 742890 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1491189 (Python Code)

Max Activating Token Index: 173