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

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

Neuron 4875 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.6870. Min Act: -0.0001

Data Index: 293196 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.2315. Min Act: -0.0000

Data Index: 483237 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.7015. Min Act: -0.0000

Data Index: 196499 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.6181. Min Act: -0.0000

Data Index: 521659 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.5015. Min Act: -0.0000

Data Index: 190935 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.3977. Min Act: -0.0000

Data Index: 163588 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.3237. Min Act: -0.0001

Data Index: 1143975 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.3167. Min Act: -0.0000

Data Index: 743966 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.1841. Min Act: -0.0001

Data Index: 673078 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.2001. Min Act: -0.0001

Data Index: 307718 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.0779. Min Act: -0.0000

Data Index: 273930 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.1493. Min Act: -0.0000

Data Index: 232363 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.1417. Min Act: -0.0000

Data Index: 815151 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 3.6870. Min Range: -3.6870

Max Act: 1.8595. Min Act: -0.0000

Data Index: 637578 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.0033. Min Act: -0.0000

Data Index: 1042446 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.0333. Min Act: -0.0000

Data Index: 1156960 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 3.6870. Min Range: -3.6870

Max Act: 2.1192. Min Act: -0.0001

Data Index: 598867 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 3.6870. Min Range: -3.6870

Max Act: 1.9893. Min Act: -0.0000

Data Index: 476052 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 3.6870. Min Range: -3.6870

Max Act: 1.9954. Min Act: -0.0000

Data Index: 1128558 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 3.6870. Min Range: -3.6870

Max Act: 1.9561. Min Act: -0.0001

Data Index: 326825 (C4 (Web Text))

Max Activating Token Index: 409