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

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

Neuron 1804 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: 0.0735. Min Range: -0.0735

Max Act: 0.0715. Min Act: -0.0003

Data Index: 297271 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0735. Min Act: -0.0004

Data Index: 928254 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0669. Min Act: -0.0004

Data Index: 337896 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0691. Min Act: -0.0003

Data Index: 303918 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0714. Min Act: -0.0004

Data Index: 333027 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0667. Min Act: -0.0003

Data Index: 883008 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0678. Min Act: -0.0003

Data Index: 371623 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0661. Min Act: -0.0003

Data Index: 448547 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0675. Min Act: -0.0003

Data Index: 365260 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0694. Min Act: -0.0003

Data Index: 317180 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0661. Min Act: -0.0003

Data Index: 695812 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0652. Min Act: -0.0004

Data Index: 619695 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0660. Min Act: -0.0003

Data Index: 528757 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1077361 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1317295 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0647. Min Act: -0.0004

Data Index: 1225256 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0672. Min Act: -0.0003

Data Index: 253736 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1311555 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0647. Min Act: -0.0003

Data Index: 838560 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0632. Min Act: -0.0004

Data Index: 1019030 (C4 (Web Text))

Max Activating Token Index: 611