Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2604 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0883. Min Act: -0.0000

Data Index: 498616 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0857. Min Act: -0.0000

Data Index: 672278 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0856. Min Act: -0.0000

Data Index: 356569 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0743. Min Act: -0.0000

Data Index: 360224 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1264867 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1035988 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1094180 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1203588 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0666. Min Act: -0.0000

Data Index: 660007 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0711. Min Act: -0.0000

Data Index: 706793 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0662. Min Act: -0.0001

Data Index: 919197 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0660. Min Act: -0.0000

Data Index: 837366 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0650. Min Act: -0.0000

Data Index: 699236 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0662. Min Act: -0.0000

Data Index: 736721 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0597. Min Act: -0.0001

Data Index: 725969 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1109342 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0614. Min Act: -0.0000

Data Index: 918382 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0582. Min Act: -0.0000

Data Index: 189520 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1147418 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1059459 (C4 (Web Text))

Max Activating Token Index: 385