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

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

Neuron 3633 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2127. Min Act: -0.0002

Data Index: 697521 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2173. Min Act: -0.0002

Data Index: 301202 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2005. Min Act: -0.0002

Data Index: 808443 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2093. Min Act: -0.0002

Data Index: 150360 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1934. Min Act: -0.0002

Data Index: 77760 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1944. Min Act: -0.0002

Data Index: 986546 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2088. Min Act: -0.0001

Data Index: 2998 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1899. Min Act: -0.0002

Data Index: 392544 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1018721 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1969. Min Act: -0.0002

Data Index: 1328144 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1770. Min Act: -0.0002

Data Index: 863834 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1783. Min Act: -0.0002

Data Index: 1070622 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1831. Min Act: -0.0002

Data Index: 859027 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1706. Min Act: -0.0002

Data Index: 1019088 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1569. Min Act: -0.0001

Data Index: 431341 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1752. Min Act: -0.0002

Data Index: 1230518 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1141320 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1675. Min Act: -0.0002

Data Index: 597312 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1135157 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1660. Min Act: -0.0001

Data Index: 471286 (C4 (Web Text))

Max Activating Token Index: 251