Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 141 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1592964 (Python Code)

Max Activating Token Index: 241

Text #1

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1404140 (Python Code)

Max Activating Token Index: 702

Text #2

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0126. Min Act: -0.0006

Data Index: 744816 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0123. Min Act: -0.0006

Data Index: 851855 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0124. Min Act: -0.0006

Data Index: 375451 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1053490 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1476300 (Python Code)

Max Activating Token Index: 504

Text #7

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0117. Min Act: -0.0006

Data Index: 538171 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0125. Min Act: -0.0006

Data Index: 126905 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1585936 (Python Code)

Max Activating Token Index: 666

Text #10

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1253773 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1278124 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1138050 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0117. Min Act: -0.0006

Data Index: 199659 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0119. Min Act: -0.0006

Data Index: 191909 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1416192 (Python Code)

Max Activating Token Index: 311

Text #16

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0115. Min Act: -0.0006

Data Index: 471219 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1184113 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0117. Min Act: -0.0006

Data Index: 913567 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1365737 (Python Code)

Max Activating Token Index: 327