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

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

Neuron 291 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1291. Min Act: -0.0000

Data Index: 594286 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1289. Min Act: -0.0000

Data Index: 336606 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1315. Min Act: 0.0000

Data Index: 398586 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1243. Min Act: -0.0000

Data Index: 788817 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1207. Min Act: -0.0001

Data Index: 158680 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1192. Min Act: 0.0000

Data Index: 1242321 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1144. Min Act: 0.0000

Data Index: 206780 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1111. Min Act: -0.0000

Data Index: 820319 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1063911 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1123. Min Act: -0.0000

Data Index: 222485 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1164. Min Act: -0.0000

Data Index: 892763 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1139. Min Act: -0.0000

Data Index: 205437 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1105663 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1079. Min Act: -0.0000

Data Index: 568198 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1327608 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1104. Min Act: -0.0000

Data Index: 921608 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1052. Min Act: -0.0000

Data Index: 853292 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1009. Min Act: -0.0000

Data Index: 978844 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1005. Min Act: -0.0000

Data Index: 305785 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1064. Min Act: -0.0000

Data Index: 154864 (C4 (Web Text))

Max Activating Token Index: 14