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

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

Neuron 868 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0005

Data Index: 546032 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0005

Data Index: 176116 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0005

Data Index: 839585 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0005

Data Index: 832988 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0005

Data Index: 841547 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0005

Data Index: 454970 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0005

Data Index: 588926 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0005

Data Index: 177455 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0005

Data Index: 133383 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0005

Data Index: 283226 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0005

Data Index: 918789 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0108. Min Act: -0.0005

Data Index: 484147 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0005

Data Index: 512928 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0005

Data Index: 102069 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0005

Data Index: 30136 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0005

Data Index: 611386 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0005

Data Index: 1345421 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0005

Data Index: 36791 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0105. Min Act: -0.0005

Data Index: 152313 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1005209 (C4 (Web Text))

Max Activating Token Index: 374