Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 9 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1555865 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0163. Min Act: -0.0003

Data Index: 164707 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1632731 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0147. Min Act: -0.0003

Data Index: 187985 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1402414 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0139. Min Act: -0.0003

Data Index: 95317 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0128. Min Act: -0.0003

Data Index: 1514819 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1432867 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1498105 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1423863 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0114. Min Act: -0.0003

Data Index: 1235738 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1584782 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1558358 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0112. Min Act: -0.0003

Data Index: 1455539 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1443899 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1458801 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0108. Min Act: -0.0003

Data Index: 668590 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1646469 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1512514 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1566046 (Python Code)

Max Activating Token Index: 1023