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

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

Neuron 1079 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: 0.1307. Min Range: -0.1307

Max Act: 0.1298. Min Act: -0.0001

Data Index: 792796 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1140457 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1304. Min Act: -0.0001

Data Index: 92134 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1184. Min Act: -0.0001

Data Index: 539176 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1149. Min Act: -0.0001

Data Index: 536277 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1207583 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1203247 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1119. Min Act: -0.0001

Data Index: 842098 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1044. Min Act: -0.0001

Data Index: 898868 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1080. Min Act: -0.0001

Data Index: 647650 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1022. Min Act: -0.0001

Data Index: 373156 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1050. Min Act: -0.0001

Data Index: 954404 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0976. Min Act: -0.0001

Data Index: 691330 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0968. Min Act: -0.0001

Data Index: 127329 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1024. Min Act: -0.0001

Data Index: 689951 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0946. Min Act: -0.0001

Data Index: 444354 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0958. Min Act: -0.0001

Data Index: 888758 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0929. Min Act: -0.0001

Data Index: 361690 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1347756 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0912. Min Act: -0.0001

Data Index: 300077 (C4 (Web Text))

Max Activating Token Index: 205