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

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

Neuron 1732 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1011. Min Act: -0.0003

Data Index: 736008 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1005. Min Act: -0.0003

Data Index: 156695 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0925. Min Act: -0.0003

Data Index: 49066 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0958. Min Act: -0.0003

Data Index: 561384 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1029. Min Act: -0.0003

Data Index: 638100 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1051. Min Act: -0.0003

Data Index: 315991 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1019. Min Act: -0.0003

Data Index: 37394 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1033. Min Act: -0.0003

Data Index: 881044 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0998. Min Act: -0.0003

Data Index: 989170 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0985. Min Act: -0.0003

Data Index: 929635 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0979. Min Act: -0.0003

Data Index: 220330 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1190234 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0900. Min Act: -0.0003

Data Index: 566330 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0910. Min Act: -0.0003

Data Index: 28166 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0922. Min Act: -0.0003

Data Index: 290127 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0951. Min Act: -0.0003

Data Index: 900276 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0865. Min Act: -0.0003

Data Index: 1025579 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0986. Min Act: -0.0003

Data Index: 242814 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0976. Min Act: -0.0003

Data Index: 692359 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0917. Min Act: -0.0003

Data Index: 29400 (C4 (Web Text))

Max Activating Token Index: 912