Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2324 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2201. Min Act: -0.0001

Data Index: 339099 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1276437 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1237717 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1196524 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1957. Min Act: -0.0001

Data Index: 1291343 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2165. Min Act: -0.0001

Data Index: 28191 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1344074 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1965. Min Act: -0.0001

Data Index: 558858 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1875. Min Act: -0.0001

Data Index: 498526 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1800. Min Act: -0.0001

Data Index: 493352 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1926. Min Act: -0.0001

Data Index: 700165 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1828. Min Act: -0.0000

Data Index: 458412 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1230716 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1838. Min Act: -0.0001

Data Index: 729156 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1837. Min Act: -0.0001

Data Index: 586124 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1654. Min Act: -0.0000

Data Index: 997391 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1770. Min Act: -0.0001

Data Index: 509427 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1097017 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1693. Min Act: -0.0000

Data Index: 769245 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1627. Min Act: -0.0001

Data Index: 606696 (C4 (Web Text))

Max Activating Token Index: 578