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

Dataset: The Pile

Neuron 1564 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3215. Min Range: -4.3215

Max Act: 4.3215. Min Act: -0.0000

Data Index: 777247 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 4.3215. Min Range: -4.3215

Max Act: 4.0606. Min Act: -0.0000

Data Index: 1492920 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.7978. Min Act: -0.0000

Data Index: 354356 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.6208. Min Act: -0.0000

Data Index: 809513 (The Pile)

Max Activating Token Index: 799

Text #4

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.6111. Min Act: -0.0000

Data Index: 972649 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.8805. Min Act: -0.0000

Data Index: 1640339 (The Pile)

Max Activating Token Index: 725

Text #6

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.4890. Min Act: -0.0000

Data Index: 301423 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.4100. Min Act: -0.0000

Data Index: 1926419 (The Pile)

Max Activating Token Index: 879

Text #8

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.5684. Min Act: -0.0000

Data Index: 698063 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.4078. Min Act: -0.0000

Data Index: 1333742 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.7348. Min Act: -0.0000

Data Index: 1094849 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.6817. Min Act: -0.0000

Data Index: 831631 (The Pile)

Max Activating Token Index: 613

Text #12

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.4070. Min Act: -0.0000

Data Index: 715545 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.2368. Min Act: -0.0000

Data Index: 470263 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 4.3215. Min Range: -4.3215

Max Act: 4.0184. Min Act: -0.0000

Data Index: 1529760 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.7786. Min Act: -0.0000

Data Index: 846505 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.1882. Min Act: -0.0000

Data Index: 1317971 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.9127. Min Act: -0.0000

Data Index: 1992167 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.4652. Min Act: -0.0000

Data Index: 299872 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 4.3215. Min Range: -4.3215

Max Act: 3.2486. Min Act: -0.0000

Data Index: 40583 (The Pile)

Max Activating Token Index: 132