Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5728 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1716. Min Act: -0.0000

Data Index: 449706 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1522. Min Act: -0.0000

Data Index: 701788 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1498. Min Act: -0.0000

Data Index: 959998 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1574. Min Act: -0.0000

Data Index: 824034 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1473. Min Act: -0.0000

Data Index: 615416 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1410. Min Act: -0.0000

Data Index: 552176 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1492. Min Act: -0.0000

Data Index: 992944 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.0920. Min Act: -0.0000

Data Index: 278709 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1217. Min Act: -0.0000

Data Index: 799346 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1114. Min Act: -0.0000

Data Index: 519660 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1100871 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1134. Min Act: -0.0000

Data Index: 788525 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1092. Min Act: -0.0000

Data Index: 794316 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1072. Min Act: -0.0000

Data Index: 652017 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1070. Min Act: -0.0000

Data Index: 196986 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1116. Min Act: -0.0000

Data Index: 141607 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1138. Min Act: -0.0000

Data Index: 448853 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1120. Min Act: -0.0000

Data Index: 882479 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1039. Min Act: -0.0000

Data Index: 692272 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.1716. Min Range: -0.1716

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1048774 (C4 (Web Text))

Max Activating Token Index: 606