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

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

Neuron 979 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: 0.0126. Min Range: -0.0126

Max Act: 0.0125. Min Act: -0.0002

Data Index: 414406 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1543755 (Python Code)

Max Activating Token Index: 29

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0125. Min Act: -0.0002

Data Index: 788525 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1078286 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0118. Min Act: -0.0002

Data Index: 354566 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1622273 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0002

Data Index: 681981 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1429818 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1599127 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1495541 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0002

Data Index: 447466 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1445436 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1006120 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0002

Data Index: 441669 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0002

Data Index: 163693 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0002

Data Index: 315322 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0002

Data Index: 125806 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1389858 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0002

Data Index: 627532 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0002

Data Index: 363655 (C4 (Web Text))

Max Activating Token Index: 8