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

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

Neuron 1812 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1301179 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0810. Min Act: -0.0002

Data Index: 689675 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0805. Min Act: -0.0002

Data Index: 936257 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0719. Min Act: -0.0002

Data Index: 409182 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0689. Min Act: -0.0002

Data Index: 998472 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1617142 (Python Code)

Max Activating Token Index: 445

Text #6

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1203918 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0673. Min Act: -0.0002

Data Index: 562604 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0579. Min Act: -0.0002

Data Index: 581133 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0610. Min Act: -0.0002

Data Index: 785911 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0683. Min Act: -0.0002

Data Index: 590496 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0677. Min Act: -0.0002

Data Index: 171440 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0604. Min Act: -0.0002

Data Index: 722505 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0609. Min Act: -0.0002

Data Index: 562968 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1045200 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0625. Min Act: -0.0002

Data Index: 190778 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1163454 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0557. Min Act: -0.0002

Data Index: 12337 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1089093 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1335180 (C4 (Web Text))

Max Activating Token Index: 521