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

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

Neuron 2293 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0650. Min Act: -0.0001

Data Index: 169698 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0001

Data Index: 732944 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0667. Min Act: -0.0001

Data Index: 918022 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0692. Min Act: -0.0001

Data Index: 756753 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1301747 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0593. Min Act: -0.0001

Data Index: 274678 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1249951 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0580. Min Act: -0.0001

Data Index: 457194 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0564. Min Act: -0.0001

Data Index: 117899 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0575. Min Act: -0.0001

Data Index: 109902 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1240865 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0590. Min Act: -0.0001

Data Index: 230696 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0588. Min Act: -0.0001

Data Index: 609222 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0521. Min Act: -0.0001

Data Index: 634024 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1178776 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1348053 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0556. Min Act: -0.0000

Data Index: 160043 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0551. Min Act: -0.0000

Data Index: 52999 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0548. Min Act: -0.0000

Data Index: 274988 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0552. Min Act: -0.0001

Data Index: 283704 (C4 (Web Text))

Max Activating Token Index: 897