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

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

Neuron 4209 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: 0.2363. Min Range: -0.2363

Max Act: 0.2332. Min Act: -0.0001

Data Index: 1282539 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2180. Min Act: -0.0001

Data Index: 457408 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2363. Min Act: -0.0001

Data Index: 230512 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2213. Min Act: -0.0001

Data Index: 147356 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1192613 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2056. Min Act: -0.0001

Data Index: 106450 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2052. Min Act: -0.0001

Data Index: 783779 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2090. Min Act: -0.0001

Data Index: 443930 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1999. Min Act: -0.0001

Data Index: 1293456 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1973. Min Act: -0.0001

Data Index: 341992 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1915. Min Act: -0.0001

Data Index: 1190825 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1923. Min Act: -0.0001

Data Index: 564441 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1842. Min Act: -0.0001

Data Index: 572258 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1773. Min Act: -0.0001

Data Index: 202640 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1758. Min Act: -0.0001

Data Index: 483459 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1884. Min Act: -0.0001

Data Index: 214481 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1821. Min Act: -0.0001

Data Index: 409012 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1052563 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1938. Min Act: -0.0001

Data Index: 413912 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2086. Min Act: -0.0001

Data Index: 354461 (C4 (Web Text))

Max Activating Token Index: 854