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

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

Neuron 1590 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0143. Min Act: -0.0004

Data Index: 363324 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0124. Min Act: -0.0005

Data Index: 545733 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0123. Min Act: -0.0004

Data Index: 373283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0126. Min Act: -0.0004

Data Index: 246577 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0123. Min Act: -0.0005

Data Index: 96174 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0119. Min Act: -0.0004

Data Index: 148985 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0123. Min Act: -0.0004

Data Index: 939662 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0118. Min Act: -0.0004

Data Index: 725698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1506696 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1220529 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0120. Min Act: -0.0004

Data Index: 439665 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0121. Min Act: -0.0004

Data Index: 1557884 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0119. Min Act: -0.0005

Data Index: 198445 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0114. Min Act: -0.0004

Data Index: 478450 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1397022 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0119. Min Act: -0.0005

Data Index: 1457369 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0121. Min Act: -0.0004

Data Index: 849703 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1638222 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1368112 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0112. Min Act: -0.0004

Data Index: 1492276 (Python Code)

Max Activating Token Index: 1023