Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1206 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1302615 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0132. Min Act: -0.0003

Data Index: 744472 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0124. Min Act: -0.0003

Data Index: 568962 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0124. Min Act: -0.0003

Data Index: 990262 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1330797 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0125. Min Act: -0.0003

Data Index: 248063 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0122. Min Act: -0.0003

Data Index: 241979 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0121. Min Act: -0.0003

Data Index: 466129 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0120. Min Act: -0.0003

Data Index: 310101 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1192188 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0121. Min Act: -0.0003

Data Index: 751575 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1511438 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1304872 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1014730 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0112. Min Act: -0.0003

Data Index: 500792 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0114. Min Act: -0.0003

Data Index: 997663 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0115. Min Act: -0.0003

Data Index: 386010 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1061761 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0114. Min Act: -0.0003

Data Index: 1444299 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0110. Min Act: -0.0003

Data Index: 661501 (C4 (Web Text))

Max Activating Token Index: 155