Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3557 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0146. Min Act: -0.0003

Data Index: 8278 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0145. Min Act: -0.0003

Data Index: 109823 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0139. Min Act: -0.0002

Data Index: 972750 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0132. Min Act: -0.0003

Data Index: 809728 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1412226 (Python Code)

Max Activating Token Index: 127

Text #5

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0127. Min Act: -0.0003

Data Index: 668843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1565119 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0124. Min Act: -0.0003

Data Index: 86765 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1350842 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1495971 (Python Code)

Max Activating Token Index: 688

Text #10

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1288569 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0122. Min Act: -0.0003

Data Index: 38646 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1166733 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1550323 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0111. Min Act: -0.0003

Data Index: 169526 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1439817 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1465247 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1505714 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0119. Min Act: -0.0003

Data Index: 442680 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0118. Min Act: -0.0003

Data Index: 18398 (C4 (Web Text))

Max Activating Token Index: 1023