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

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

Neuron 441 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0005

Data Index: 92009 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1235850 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0133. Min Act: -0.0005

Data Index: 461183 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0128. Min Act: -0.0005

Data Index: 1311407 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1148677 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1461398 (Python Code)

Max Activating Token Index: 189

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0127. Min Act: -0.0005

Data Index: 1370438 (Python Code)

Max Activating Token Index: 185

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0127. Min Act: -0.0005

Data Index: 366161 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0126. Min Act: -0.0006

Data Index: 671474 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0126. Min Act: -0.0005

Data Index: 90965 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0125. Min Act: -0.0005

Data Index: 918788 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0123. Min Act: -0.0005

Data Index: 370181 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0121. Min Act: -0.0005

Data Index: 892604 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0120. Min Act: -0.0006

Data Index: 758510 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0120. Min Act: -0.0005

Data Index: 54590 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0119. Min Act: -0.0006

Data Index: 604569 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1430149 (Python Code)

Max Activating Token Index: 860

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0118. Min Act: -0.0006

Data Index: 828333 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1502148 (Python Code)

Max Activating Token Index: 904

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0117. Min Act: -0.0005

Data Index: 726382 (C4 (Web Text))

Max Activating Token Index: 992