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

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

Neuron 3645 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8346. Min Act: -0.0000

Data Index: 856778 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.5542. Min Act: -0.0001

Data Index: 53066 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1205980 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.4614. Min Act: -0.0000

Data Index: 504968 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1283460 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.4428. Min Act: -0.0000

Data Index: 492100 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.4218. Min Act: -0.0000

Data Index: 778660 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.4200. Min Act: -0.0001

Data Index: 253534 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.4420. Min Act: -0.0000

Data Index: 167998 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.4144. Min Act: -0.0000

Data Index: 704011 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.4119. Min Act: -0.0000

Data Index: 918243 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.3949. Min Act: -0.0000

Data Index: 594485 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.4032. Min Act: -0.0001

Data Index: 224920 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.3765. Min Act: -0.0001

Data Index: 275319 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1341841 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.3783. Min Act: -0.0000

Data Index: 662585 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.3799. Min Act: -0.0000

Data Index: 931147 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.3910. Min Act: -0.0000

Data Index: 916227 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.3642. Min Act: -0.0000

Data Index: 639631 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1196208 (C4 (Web Text))

Max Activating Token Index: 711