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

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

Neuron 61 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1433735 (Python Code)

Max Activating Token Index: 298

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0006

Data Index: 851520 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1292935 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0130. Min Act: -0.0006

Data Index: 761843 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0136. Min Act: -0.0006

Data Index: 711776 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0006

Data Index: 939884 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0121. Min Act: -0.0006

Data Index: 149822 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0006

Data Index: 414763 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1175830 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0119. Min Act: -0.0006

Data Index: 218870 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0122. Min Act: -0.0006

Data Index: 351885 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1350891 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0123. Min Act: -0.0006

Data Index: 91114 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0120. Min Act: -0.0006

Data Index: 951429 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1160493 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1264467 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0120. Min Act: -0.0006

Data Index: 587226 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0128. Min Act: -0.0006

Data Index: 923476 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1313850 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1275145 (C4 (Web Text))

Max Activating Token Index: 928