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

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

Neuron 368 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: 0.1157. Min Range: -0.1157

Max Act: 0.1150. Min Act: -0.0001

Data Index: 34195 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1105. Min Act: -0.0000

Data Index: 491858 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1199394 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1130. Min Act: -0.0001

Data Index: 930164 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1081. Min Act: -0.0000

Data Index: 499373 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0996. Min Act: -0.0000

Data Index: 197518 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1294828 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1157. Min Act: -0.0001

Data Index: 876972 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1070258 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1027. Min Act: -0.0000

Data Index: 999728 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0991. Min Act: -0.0000

Data Index: 426678 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0987. Min Act: -0.0000

Data Index: 616656 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1180917 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1057. Min Act: -0.0001

Data Index: 210633 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1062. Min Act: -0.0000

Data Index: 768253 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0905. Min Act: -0.0001

Data Index: 866002 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0940. Min Act: -0.0001

Data Index: 416244 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1104259 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0936. Min Act: -0.0000

Data Index: 96965 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0896. Min Act: -0.0001

Data Index: 749886 (C4 (Web Text))

Max Activating Token Index: 491