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

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

Neuron 2955 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0206. Min Act: -0.0003

Data Index: 755035 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0149. Min Act: -0.0003

Data Index: 616495 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1022078 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1636932 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0141. Min Act: -0.0003

Data Index: 644257 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0139. Min Act: -0.0003

Data Index: 914072 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0139. Min Act: -0.0003

Data Index: 729506 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0134. Min Act: -0.0002

Data Index: 884988 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0128. Min Act: -0.0002

Data Index: 47078 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0134. Min Act: -0.0002

Data Index: 658409 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0129. Min Act: -0.0003

Data Index: 790398 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1428143 (Python Code)

Max Activating Token Index: 844

Text #12

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1087734 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0112. Min Act: -0.0003

Data Index: 1228670 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1539695 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0117. Min Act: -0.0003

Data Index: 908655 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0119. Min Act: -0.0002

Data Index: 368356 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1162547 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0111. Min Act: -0.0002

Data Index: 479678 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0115. Min Act: -0.0003

Data Index: 118006 (C4 (Web Text))

Max Activating Token Index: 31