Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 995 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1216741 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1195. Min Act: -0.0001

Data Index: 240496 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1205. Min Act: -0.0001

Data Index: 944451 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1162. Min Act: -0.0001

Data Index: 93023 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1306975 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1036. Min Act: -0.0001

Data Index: 886677 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1077. Min Act: -0.0001

Data Index: 54648 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1014. Min Act: -0.0001

Data Index: 54642 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1233255 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1250144 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1022505 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1025. Min Act: -0.0001

Data Index: 568782 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1078. Min Act: -0.0001

Data Index: 327346 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1311341 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1051. Min Act: -0.0001

Data Index: 110349 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0997. Min Act: -0.0001

Data Index: 663323 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1000. Min Act: -0.0001

Data Index: 503794 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1038. Min Act: -0.0001

Data Index: 792386 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1064266 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1017. Min Act: -0.0001

Data Index: 1309643 (C4 (Web Text))

Max Activating Token Index: 994