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

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

Neuron 83 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: 0.0639. Min Range: -0.0639

Max Act: 0.0639. Min Act: -0.0004

Data Index: 278368 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0608. Min Act: -0.0004

Data Index: 4416 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0596. Min Act: -0.0003

Data Index: 117254 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0613. Min Act: -0.0004

Data Index: 641930 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0611. Min Act: -0.0003

Data Index: 771382 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0589. Min Act: -0.0003

Data Index: 573802 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0573. Min Act: -0.0003

Data Index: 194790 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0579. Min Act: -0.0003

Data Index: 831988 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1072480 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0566. Min Act: -0.0003

Data Index: 299218 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0560. Min Act: -0.0003

Data Index: 602273 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0555. Min Act: -0.0004

Data Index: 998360 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0538. Min Act: -0.0003

Data Index: 1062205 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0550. Min Act: -0.0003

Data Index: 958438 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0535. Min Act: -0.0003

Data Index: 913552 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0539. Min Act: -0.0003

Data Index: 466022 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1227892 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0540. Min Act: -0.0003

Data Index: 851506 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0530. Min Act: -0.0004

Data Index: 297203 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1296176 (C4 (Web Text))

Max Activating Token Index: 775