Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1109 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1205. Min Act: -0.0006

Data Index: 784205 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1134. Min Act: -0.0006

Data Index: 934252 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1125. Min Act: -0.0006

Data Index: 112592 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1101. Min Act: -0.0006

Data Index: 1041505 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1085. Min Act: -0.0006

Data Index: 667654 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1116. Min Act: -0.0006

Data Index: 166772 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1051. Min Act: -0.0006

Data Index: 69229 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1096. Min Act: -0.0006

Data Index: 907877 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1058. Min Act: -0.0006

Data Index: 1178915 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1002. Min Act: -0.0006

Data Index: 4269 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1003. Min Act: -0.0006

Data Index: 1231186 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0997. Min Act: -0.0006

Data Index: 721902 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0994. Min Act: -0.0006

Data Index: 938855 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0972. Min Act: -0.0006

Data Index: 735857 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0932. Min Act: -0.0006

Data Index: 762689 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0956. Min Act: -0.0006

Data Index: 130130 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0918. Min Act: -0.0006

Data Index: 574505 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0874. Min Act: -0.0006

Data Index: 853465 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0905. Min Act: -0.0006

Data Index: 1107401 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0933. Min Act: -0.0006

Data Index: 707537 (C4 (Web Text))

Max Activating Token Index: 748