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

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

Neuron 819 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0005

Data Index: 550548 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0772. Min Act: -0.0006

Data Index: 856810 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0791. Min Act: -0.0006

Data Index: 391250 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0702. Min Act: -0.0006

Data Index: 896980 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0696. Min Act: -0.0006

Data Index: 480732 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0634. Min Act: -0.0006

Data Index: 673545 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0564. Min Act: -0.0006

Data Index: 907012 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0586. Min Act: -0.0006

Data Index: 462676 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0627. Min Act: -0.0006

Data Index: 439362 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0672. Min Act: -0.0006

Data Index: 723029 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0642. Min Act: -0.0006

Data Index: 1302719 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0590. Min Act: -0.0005

Data Index: 388411 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0636. Min Act: -0.0006

Data Index: 1316607 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0654. Min Act: -0.0006

Data Index: 1280330 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0627. Min Act: -0.0006

Data Index: 341783 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0599. Min Act: -0.0006

Data Index: 395740 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0601. Min Act: -0.0006

Data Index: 459769 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0609. Min Act: -0.0006

Data Index: 1030894 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0591. Min Act: -0.0006

Data Index: 842193 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0602. Min Act: -0.0005

Data Index: 1265791 (C4 (Web Text))

Max Activating Token Index: 14