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

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

Neuron 1059 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1389685 (Python Code)

Max Activating Token Index: 114

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0115. Min Act: -0.0002

Data Index: 602010 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0114. Min Act: -0.0002

Data Index: 742812 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1316619 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1463640 (Python Code)

Max Activating Token Index: 155

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0113. Min Act: -0.0002

Data Index: 11672 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1233378 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0112. Min Act: -0.0002

Data Index: 322381 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0112. Min Act: -0.0002

Data Index: 848633 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1574203 (Python Code)

Max Activating Token Index: 928

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0111. Min Act: -0.0002

Data Index: 51490 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1069752 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0111. Min Act: -0.0002

Data Index: 697002 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1360046 (Python Code)

Max Activating Token Index: 757

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0110. Min Act: -0.0002

Data Index: 265222 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0110. Min Act: -0.0002

Data Index: 962990 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0110. Min Act: -0.0002

Data Index: 911069 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0110. Min Act: -0.0002

Data Index: 928484 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0110. Min Act: -0.0002

Data Index: 246224 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0110. Min Act: -0.0002

Data Index: 892359 (C4 (Web Text))

Max Activating Token Index: 4