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

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

Neuron 1817 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8501. Min Act: -0.0000

Data Index: 782088 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.6591. Min Act: -0.0000

Data Index: 91213 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.7899. Min Act: -0.0000

Data Index: 379694 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.7262. Min Act: -0.0000

Data Index: 45698 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.6664. Min Act: -0.0000

Data Index: 1309674 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.4866. Min Act: -0.0000

Data Index: 363678 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.4382. Min Act: -0.0000

Data Index: 752476 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.4609. Min Act: -0.0000

Data Index: 464469 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.4635. Min Act: -0.0000

Data Index: 37105 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.5094. Min Act: -0.0000

Data Index: 732406 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.3802. Min Act: -0.0000

Data Index: 1111287 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.4967. Min Act: -0.0000

Data Index: 719209 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.4366. Min Act: -0.0000

Data Index: 1078893 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.4116. Min Act: -0.0000

Data Index: 935832 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.3781. Min Act: -0.0000

Data Index: 439342 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.4859. Min Act: -0.0000

Data Index: 832992 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.3764. Min Act: -0.0000

Data Index: 988911 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.4242. Min Act: -0.0000

Data Index: 959001 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.4294. Min Act: -0.0000

Data Index: 154528 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.4161. Min Act: -0.0000

Data Index: 682171 (C4 (Web Text))

Max Activating Token Index: 811