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

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

Neuron 794 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1014. Min Act: -0.0002

Data Index: 39418 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1198031 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1172. Min Act: -0.0002

Data Index: 675629 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1156. Min Act: -0.0001

Data Index: 139023 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1202. Min Act: -0.0002

Data Index: 574829 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1206. Min Act: -0.0002

Data Index: 111728 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1109. Min Act: -0.0002

Data Index: 563664 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1135. Min Act: -0.0002

Data Index: 145033 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1086. Min Act: -0.0002

Data Index: 1160771 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1084. Min Act: -0.0002

Data Index: 827851 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1115. Min Act: -0.0002

Data Index: 951797 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1068. Min Act: -0.0002

Data Index: 19940 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1102. Min Act: -0.0002

Data Index: 869183 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1105. Min Act: -0.0002

Data Index: 736784 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1081. Min Act: -0.0002

Data Index: 582221 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1057. Min Act: -0.0002

Data Index: 661488 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1114. Min Act: -0.0001

Data Index: 894787 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1076. Min Act: -0.0001

Data Index: 146747 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1067. Min Act: -0.0002

Data Index: 168450 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1113. Min Act: -0.0002

Data Index: 631585 (C4 (Web Text))

Max Activating Token Index: 285