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

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

Neuron 620 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0001

Data Index: 885928 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0698. Min Act: -0.0001

Data Index: 665416 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0662. Min Act: -0.0001

Data Index: 288525 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1097410 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0704. Min Act: -0.0001

Data Index: 785386 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1316009 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0582. Min Act: -0.0001

Data Index: 821408 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0615. Min Act: -0.0001

Data Index: 809737 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0649. Min Act: -0.0001

Data Index: 570476 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0646. Min Act: -0.0001

Data Index: 958938 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0574. Min Act: -0.0001

Data Index: 506846 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0576. Min Act: -0.0001

Data Index: 850603 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0639. Min Act: -0.0001

Data Index: 772152 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1028840 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1209717 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0559. Min Act: -0.0001

Data Index: 716377 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0528. Min Act: -0.0001

Data Index: 941438 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0502. Min Act: -0.0001

Data Index: 1090908 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1176061 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1028954 (C4 (Web Text))

Max Activating Token Index: 35