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

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

Neuron 81 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1013936 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1155. Min Act: -0.0002

Data Index: 830261 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1070. Min Act: -0.0002

Data Index: 3686 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1069. Min Act: -0.0002

Data Index: 1053674 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1077. Min Act: -0.0002

Data Index: 302986 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1112. Min Act: -0.0002

Data Index: 206757 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0989. Min Act: -0.0002

Data Index: 491030 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1085. Min Act: -0.0002

Data Index: 232835 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1083. Min Act: -0.0002

Data Index: 884626 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1188885 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1025. Min Act: -0.0002

Data Index: 381810 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1196. Min Act: -0.0002

Data Index: 95931 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1353756 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1022430 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1162. Min Act: -0.0002

Data Index: 991699 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0960. Min Act: -0.0002

Data Index: 11376 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1008. Min Act: -0.0002

Data Index: 219389 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0917. Min Act: -0.0002

Data Index: 972062 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0987. Min Act: -0.0002

Data Index: 330263 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1013. Min Act: -0.0002

Data Index: 353858 (C4 (Web Text))

Max Activating Token Index: 457