Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3631 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1306904 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2667. Min Act: -0.0001

Data Index: 118374 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2396. Min Act: -0.0000

Data Index: 957478 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2317. Min Act: -0.0001

Data Index: 147614 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2113. Min Act: -0.0000

Data Index: 754634 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2122. Min Act: -0.0001

Data Index: 10550 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2044. Min Act: -0.0001

Data Index: 365575 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2155. Min Act: -0.0000

Data Index: 861867 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2184. Min Act: -0.0001

Data Index: 898162 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1915. Min Act: -0.0001

Data Index: 334755 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2114. Min Act: -0.0000

Data Index: 253158 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1870. Min Act: -0.0000

Data Index: 568973 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2096. Min Act: -0.0001

Data Index: 251197 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1847. Min Act: -0.0000

Data Index: 726015 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2013. Min Act: -0.0000

Data Index: 675170 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1775. Min Act: -0.0000

Data Index: 743911 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1856. Min Act: -0.0000

Data Index: 673284 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1283284 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1737. Min Act: -0.0001

Data Index: 707170 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1087964 (C4 (Web Text))

Max Activating Token Index: 583