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

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

Neuron 5102 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1450275 (Python Code)

Max Activating Token Index: 1019

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1510353 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1584787 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1465766 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0156. Min Act: -0.0002

Data Index: 227964 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1528732 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1603649 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0156. Min Act: -0.0002

Data Index: 942075 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1628053 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0101. Min Act: -0.0002

Data Index: 1572280 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1656439 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1363815 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0147. Min Act: -0.0002

Data Index: 510315 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1600565 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0112. Min Act: -0.0002

Data Index: 155623 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1619481 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1198883 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1395846 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1283897 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0089. Min Act: -0.0002

Data Index: 229428 (C4 (Web Text))

Max Activating Token Index: 221