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

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

Neuron 2165 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2642. Min Act: -0.0001

Data Index: 815290 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2296. Min Act: -0.0001

Data Index: 342022 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2198. Min Act: -0.0001

Data Index: 409516 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2087. Min Act: -0.0001

Data Index: 936199 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2051. Min Act: -0.0001

Data Index: 818332 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2003. Min Act: -0.0000

Data Index: 95570 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2064. Min Act: -0.0001

Data Index: 218357 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1082197 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1956. Min Act: -0.0000

Data Index: 951045 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2013. Min Act: -0.0000

Data Index: 340255 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1931. Min Act: -0.0000

Data Index: 229597 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1867. Min Act: -0.0000

Data Index: 758892 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1830. Min Act: -0.0001

Data Index: 141549 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1042129 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1263945 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1867. Min Act: -0.0000

Data Index: 70791 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1861. Min Act: -0.0001

Data Index: 1066465 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1709. Min Act: -0.0001

Data Index: 528029 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1787. Min Act: -0.0001

Data Index: 176999 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1779. Min Act: -0.0000

Data Index: 994101 (C4 (Web Text))

Max Activating Token Index: 36