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

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

Neuron 1852 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2452. Min Act: -0.0001

Data Index: 1460663 (Python Code)

Max Activating Token Index: 849

Text #1

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2198. Min Act: -0.0001

Data Index: 143357 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2119. Min Act: -0.0001

Data Index: 84146 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2085. Min Act: -0.0001

Data Index: 1253054 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2113. Min Act: -0.0001

Data Index: 1032781 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2125. Min Act: -0.0001

Data Index: 458497 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2058. Min Act: -0.0001

Data Index: 480290 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2006. Min Act: -0.0001

Data Index: 1377973 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1879. Min Act: -0.0001

Data Index: 1182105 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1938. Min Act: -0.0001

Data Index: 1067380 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1982. Min Act: -0.0001

Data Index: 206950 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1937. Min Act: -0.0001

Data Index: 555439 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1982. Min Act: -0.0001

Data Index: 38172 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1893. Min Act: -0.0000

Data Index: 646441 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2037. Min Act: -0.0001

Data Index: 264959 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2037. Min Act: -0.0001

Data Index: 330596 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1737. Min Act: -0.0001

Data Index: 782394 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1761. Min Act: -0.0001

Data Index: 859370 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1695. Min Act: -0.0001

Data Index: 686280 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1727. Min Act: -0.0001

Data Index: 1061071 (C4 (Web Text))

Max Activating Token Index: 737