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

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

Neuron 1063 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0001

Data Index: 917441 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1116. Min Act: -0.0001

Data Index: 860036 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1696 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1115. Min Act: -0.0001

Data Index: 149069 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1126. Min Act: -0.0001

Data Index: 419747 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1020601 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1101. Min Act: -0.0001

Data Index: 179512 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0991. Min Act: 0.0001

Data Index: 348359 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0931. Min Act: -0.0001

Data Index: 767457 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1243326 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0969. Min Act: -0.0000

Data Index: 483789 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1028. Min Act: -0.0001

Data Index: 606720 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0944. Min Act: -0.0001

Data Index: 546749 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0949. Min Act: -0.0001

Data Index: 776541 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0930. Min Act: -0.0001

Data Index: 613966 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0935. Min Act: -0.0001

Data Index: 632687 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1186088 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0926. Min Act: -0.0001

Data Index: 975193 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1173618 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0890. Min Act: -0.0001

Data Index: 425133 (C4 (Web Text))

Max Activating Token Index: 270