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

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

Neuron 2530 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1629610 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0155. Min Act: -0.0003

Data Index: 119210 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0152. Min Act: -0.0003

Data Index: 865913 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1510838 (Python Code)

Max Activating Token Index: 878

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1090137 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1404385 (Python Code)

Max Activating Token Index: 897

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0137. Min Act: -0.0003

Data Index: 149554 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0144. Min Act: -0.0003

Data Index: 1553592 (Python Code)

Max Activating Token Index: 525

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0143. Min Act: -0.0003

Data Index: 649843 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0136. Min Act: -0.0003

Data Index: 719822 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0127. Min Act: -0.0003

Data Index: 303795 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1392047 (Python Code)

Max Activating Token Index: 1003

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0134. Min Act: -0.0003

Data Index: 410379 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0133. Min Act: -0.0003

Data Index: 355774 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1647607 (Python Code)

Max Activating Token Index: 884

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1195940 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1503668 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1620357 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1607046 (Python Code)

Max Activating Token Index: 927

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1642652 (Python Code)

Max Activating Token Index: 407