Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3636 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1105870 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1257. Min Act: -0.0000

Data Index: 928696 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1333. Min Act: -0.0000

Data Index: 966943 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1125. Min Act: -0.0000

Data Index: 892118 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1167. Min Act: -0.0000

Data Index: 939201 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1125. Min Act: -0.0000

Data Index: 962853 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1079. Min Act: -0.0000

Data Index: 742665 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1214. Min Act: -0.0000

Data Index: 195146 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1150381 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1228. Min Act: -0.0000

Data Index: 34211 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1181385 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1169. Min Act: -0.0000

Data Index: 509022 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1170. Min Act: -0.0000

Data Index: 601124 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1313822 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1085. Min Act: -0.0000

Data Index: 322763 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1134988 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1151732 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1044. Min Act: -0.0000

Data Index: 918464 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1057. Min Act: -0.0000

Data Index: 188214 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1210241 (C4 (Web Text))

Max Activating Token Index: 372