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

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

Neuron 3399 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1357. Min Act: -0.0002

Data Index: 348593 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1269. Min Act: -0.0002

Data Index: 1134433 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1257. Min Act: -0.0002

Data Index: 31692 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1223. Min Act: -0.0002

Data Index: 121362 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1221. Min Act: -0.0002

Data Index: 493903 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1152. Min Act: -0.0002

Data Index: 1272359 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1170. Min Act: -0.0002

Data Index: 689834 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1160. Min Act: -0.0002

Data Index: 220476 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1149. Min Act: -0.0002

Data Index: 281681 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1144. Min Act: -0.0002

Data Index: 1643484 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1112. Min Act: -0.0002

Data Index: 212687 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1118. Min Act: -0.0002

Data Index: 415114 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1167013 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1109. Min Act: -0.0002

Data Index: 743880 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1636180 (Python Code)

Max Activating Token Index: 444

Text #15

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1080. Min Act: -0.0002

Data Index: 619175 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1097. Min Act: -0.0002

Data Index: 407922 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1086. Min Act: -0.0002

Data Index: 115677 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1069. Min Act: -0.0002

Data Index: 712752 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1078. Min Act: -0.0002

Data Index: 94768 (C4 (Web Text))

Max Activating Token Index: 501