Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 234 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0843. Min Act: -0.0003

Data Index: 852523 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1021852 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0764. Min Act: -0.0003

Data Index: 145484 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0692. Min Act: -0.0003

Data Index: 989265 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1325689 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1187121 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0627. Min Act: -0.0003

Data Index: 1150883 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0662. Min Act: -0.0003

Data Index: 9095 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0637. Min Act: -0.0004

Data Index: 1341918 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0633. Min Act: -0.0003

Data Index: 499522 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0621. Min Act: -0.0003

Data Index: 95973 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0629. Min Act: -0.0003

Data Index: 388783 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0641. Min Act: -0.0003

Data Index: 411074 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0649. Min Act: -0.0004

Data Index: 1053387 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0646. Min Act: -0.0003

Data Index: 207328 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1159210 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0589. Min Act: -0.0003

Data Index: 288013 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0608. Min Act: -0.0003

Data Index: 396335 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0631. Min Act: -0.0003

Data Index: 721556 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1349695 (C4 (Web Text))

Max Activating Token Index: 192