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

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

Neuron 4670 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: 0.0154. Min Range: -0.0154

Max Act: 0.0144. Min Act: -0.0003

Data Index: 1426115 (Python Code)

Max Activating Token Index: 956

Text #1

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1434812 (Python Code)

Max Activating Token Index: 766

Text #2

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1506960 (Python Code)

Max Activating Token Index: 668

Text #3

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1598134 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1233843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0126. Min Act: -0.0003

Data Index: 586603 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1629369 (Python Code)

Max Activating Token Index: 900

Text #7

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1567406 (Python Code)

Max Activating Token Index: 980

Text #8

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1528019 (Python Code)

Max Activating Token Index: 950

Text #9

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1460739 (Python Code)

Max Activating Token Index: 252

Text #10

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1627920 (Python Code)

Max Activating Token Index: 467

Text #11

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1613508 (Python Code)

Max Activating Token Index: 400

Text #12

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0111. Min Act: -0.0003

Data Index: 374617 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1426507 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1420214 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1585199 (Python Code)

Max Activating Token Index: 852

Text #16

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1214577 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1556140 (Python Code)

Max Activating Token Index: 121

Text #18

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1387080 (Python Code)

Max Activating Token Index: 42

Text #19

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1623400 (Python Code)

Max Activating Token Index: 715