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

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

Neuron 3491 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0732. Min Range: -1.0732

Max Act: 1.0732. Min Act: -0.0000

Data Index: 1605579 (Python Code)

Max Activating Token Index: 589

Text #1

Max Range: 1.0732. Min Range: -1.0732

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1545599 (Python Code)

Max Activating Token Index: 903

Text #2

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.9108. Min Act: -0.0001

Data Index: 1113137 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1620914 (Python Code)

Max Activating Token Index: 852

Text #4

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8627. Min Act: -0.0000

Data Index: 82718 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.9211. Min Act: -0.0000

Data Index: 628416 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.9355. Min Act: -0.0000

Data Index: 240583 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8840. Min Act: -0.0000

Data Index: 412105 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8954. Min Act: -0.0000

Data Index: 829707 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1404609 (Python Code)

Max Activating Token Index: 967

Text #10

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8574. Min Act: -0.0001

Data Index: 318558 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8994. Min Act: -0.0001

Data Index: 1620835 (Python Code)

Max Activating Token Index: 417

Text #12

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1147614 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1122081 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1419632 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8849. Min Act: -0.0000

Data Index: 209166 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.9045. Min Act: -0.0000

Data Index: 449844 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8045. Min Act: -0.0001

Data Index: 145093 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8847. Min Act: -0.0001

Data Index: 1528862 (Python Code)

Max Activating Token Index: 182

Text #19

Max Range: 1.0732. Min Range: -1.0732

Max Act: 0.8219. Min Act: -0.0000

Data Index: 778937 (C4 (Web Text))

Max Activating Token Index: 198