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

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

Neuron 4472 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: 1.8765. Min Range: -1.8765

Max Act: 1.8765. Min Act: -0.0000

Data Index: 788947 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.6767. Min Act: -0.0000

Data Index: 980965 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.4994. Min Act: -0.0000

Data Index: 858565 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.4852. Min Act: -0.0000

Data Index: 649538 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.4012. Min Act: -0.0000

Data Index: 1105118 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.4206. Min Act: -0.0000

Data Index: 10386 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1021795 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.4695. Min Act: -0.0000

Data Index: 1304417 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.2851. Min Act: -0.0000

Data Index: 682107 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.3516. Min Act: -0.0000

Data Index: 1121912 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.3398. Min Act: -0.0000

Data Index: 648691 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.3832. Min Act: -0.0000

Data Index: 475409 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.2828. Min Act: -0.0000

Data Index: 804750 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.2784. Min Act: -0.0000

Data Index: 185163 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.2063. Min Act: -0.0000

Data Index: 682061 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1044189 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.1435. Min Act: -0.0000

Data Index: 1199234 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.1470. Min Act: -0.0000

Data Index: 1315918 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.1501. Min Act: -0.0000

Data Index: 189697 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 1.8765. Min Range: -1.8765

Max Act: 1.1060. Min Act: -0.0000

Data Index: 869105 (C4 (Web Text))

Max Activating Token Index: 79