Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1821 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.4067. Min Act: -0.0001

Data Index: 1291452 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.5721. Min Act: -0.0001

Data Index: 146864 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.4038. Min Act: -0.0001

Data Index: 336639 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.3808. Min Act: -0.0001

Data Index: 574753 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.3645. Min Act: -0.0001

Data Index: 163886 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.3255. Min Act: -0.0001

Data Index: 1078701 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.2030. Min Act: -0.0001

Data Index: 586483 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.1821. Min Act: -0.0001

Data Index: 1080986 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.1238. Min Act: -0.0001

Data Index: 997708 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.0953. Min Act: -0.0001

Data Index: 1115833 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.2226. Min Act: -0.0001

Data Index: 955337 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.1737. Min Act: -0.0001

Data Index: 941079 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.0980. Min Act: -0.0001

Data Index: 107345 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.1015. Min Act: -0.0001

Data Index: 1048543 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.1573. Min Act: -0.0001

Data Index: 574908 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.1193. Min Act: -0.0001

Data Index: 1312708 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.0408. Min Act: -0.0001

Data Index: 779591 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.1017. Min Act: -0.0001

Data Index: 938470 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.1392. Min Act: -0.0001

Data Index: 261068 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 1.5721. Min Range: -1.5721

Max Act: 1.1805. Min Act: -0.0001

Data Index: 822988 (C4 (Web Text))

Max Activating Token Index: 807