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

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

Neuron 2904 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: 5.0026. Min Range: -5.0026

Max Act: 4.9681. Min Act: -0.0001

Data Index: 1241998 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.9767. Min Act: -0.0001

Data Index: 542179 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 5.0026. Min Range: -5.0026

Max Act: 5.0026. Min Act: -0.0001

Data Index: 216426 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.4359. Min Act: -0.0001

Data Index: 307471 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.5941. Min Act: -0.0001

Data Index: 1117866 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.7597. Min Act: -0.0001

Data Index: 60673 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.5072. Min Act: -0.0001

Data Index: 1242016 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.5974. Min Act: -0.0001

Data Index: 574185 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.6617. Min Act: -0.0001

Data Index: 457062 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.6522. Min Act: -0.0001

Data Index: 112220 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.5016. Min Act: -0.0001

Data Index: 25625 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.6540. Min Act: -0.0001

Data Index: 507130 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.4251. Min Act: -0.0001

Data Index: 628142 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.5355. Min Act: -0.0001

Data Index: 324516 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.0297. Min Act: -0.0001

Data Index: 45922 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 5.0026. Min Range: -5.0026

Max Act: 4.3035. Min Act: -0.0001

Data Index: 889737 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 5.0026. Min Range: -5.0026

Max Act: 3.6899. Min Act: -0.0001

Data Index: 190842 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 5.0026. Min Range: -5.0026

Max Act: 3.5152. Min Act: -0.0001

Data Index: 1261303 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 5.0026. Min Range: -5.0026

Max Act: 3.8084. Min Act: -0.0001

Data Index: 237767 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 5.0026. Min Range: -5.0026

Max Act: 3.2666. Min Act: -0.0001

Data Index: 852742 (C4 (Web Text))

Max Activating Token Index: 929