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

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

Neuron 574 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: 0.0214. Min Range: -0.0214

Max Act: 0.0214. Min Act: -0.0006

Data Index: 338797 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0149. Min Act: -0.0006

Data Index: 822035 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0135. Min Act: -0.0006

Data Index: 794988 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0132. Min Act: -0.0006

Data Index: 570921 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0131. Min Act: -0.0006

Data Index: 947257 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0133. Min Act: -0.0006

Data Index: 507784 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0117. Min Act: -0.0006

Data Index: 908230 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0126. Min Act: -0.0006

Data Index: 331523 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1087636 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1220976 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0123. Min Act: -0.0006

Data Index: 919955 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0114. Min Act: -0.0006

Data Index: 865046 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1038543 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1150344 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0108. Min Act: -0.0006

Data Index: 784339 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0112. Min Act: -0.0005

Data Index: 748321 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0115. Min Act: -0.0006

Data Index: 200940 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1341669 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1178659 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0112. Min Act: -0.0006

Data Index: 545139 (C4 (Web Text))

Max Activating Token Index: 565