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

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

Neuron 2608 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1230. Min Act: -0.0001

Data Index: 52697 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1333817 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1100. Min Act: -0.0001

Data Index: 750036 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1344337 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1167. Min Act: -0.0001

Data Index: 808972 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1182. Min Act: -0.0001

Data Index: 1354147 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1144. Min Act: -0.0001

Data Index: 491842 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1203. Min Act: -0.0001

Data Index: 1600349 (Python Code)

Max Activating Token Index: 334

Text #8

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1172. Min Act: -0.0001

Data Index: 806296 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1115. Min Act: -0.0001

Data Index: 553146 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1110. Min Act: -0.0001

Data Index: 309552 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1156242 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1199080 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1053. Min Act: -0.0001

Data Index: 696929 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1088. Min Act: -0.0001

Data Index: 554636 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1039085 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1033. Min Act: -0.0001

Data Index: 895631 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1109. Min Act: -0.0001

Data Index: 939068 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1068. Min Act: -0.0001

Data Index: 226065 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1055. Min Act: -0.0001

Data Index: 438002 (C4 (Web Text))

Max Activating Token Index: 423