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

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

Neuron 36 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.3249. Min Act: -0.0000

Data Index: 899922 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1190554 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1133914 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1082. Min Act: -0.0000

Data Index: 622128 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1213. Min Act: -0.0000

Data Index: 676928 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1295. Min Act: -0.0000

Data Index: 1107391 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1024. Min Act: -0.0000

Data Index: 928192 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1055. Min Act: -0.0000

Data Index: 570927 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1040. Min Act: -0.0000

Data Index: 880029 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1144121 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1637762 (Python Code)

Max Activating Token Index: 739

Text #11

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.1027. Min Act: -0.0000

Data Index: 892486 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.0970. Min Act: -0.0000

Data Index: 400006 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.0932. Min Act: -0.0000

Data Index: 357088 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.0971. Min Act: -0.0000

Data Index: 737454 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1196262 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.0862. Min Act: -0.0000

Data Index: 108935 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.0950. Min Act: -0.0000

Data Index: 968821 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.0916. Min Act: -0.0000

Data Index: 213555 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.3249. Min Range: -0.3249

Max Act: 0.0950. Min Act: -0.0000

Data Index: 965770 (C4 (Web Text))

Max Activating Token Index: 775