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

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

Neuron 1608 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.5707. Min Act: -0.0001

Data Index: 45751 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4074. Min Act: -0.0001

Data Index: 175174 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.2933. Min Act: -0.0001

Data Index: 1283480 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.3240. Min Act: -0.0001

Data Index: 418096 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.2347. Min Act: -0.0001

Data Index: 161382 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.1826. Min Act: -0.0001

Data Index: 37742 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.0093. Min Act: -0.0001

Data Index: 758686 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.1663. Min Act: -0.0001

Data Index: 145479 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.0555. Min Act: -0.0001

Data Index: 232405 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.0458. Min Act: -0.0001

Data Index: 959327 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.0283. Min Act: -0.0001

Data Index: 555616 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.0132. Min Act: -0.0001

Data Index: 294602 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.5707. Min Range: -1.5707

Max Act: 0.9991. Min Act: -0.0001

Data Index: 691145 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.5707. Min Range: -1.5707

Max Act: 0.8696. Min Act: -0.0001

Data Index: 535177 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 1.5707. Min Range: -1.5707

Max Act: 0.9695. Min Act: -0.0001

Data Index: 1355277 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 1.5707. Min Range: -1.5707

Max Act: 0.9759. Min Act: -0.0001

Data Index: 1161297 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 1.5707. Min Range: -1.5707

Max Act: 0.9712. Min Act: -0.0001

Data Index: 892240 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 1.5707. Min Range: -1.5707

Max Act: 0.9468. Min Act: -0.0001

Data Index: 1328688 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.5707. Min Range: -1.5707

Max Act: 0.9840. Min Act: -0.0001

Data Index: 542835 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 1.5707. Min Range: -1.5707

Max Act: 0.8679. Min Act: -0.0001

Data Index: 723764 (C4 (Web Text))

Max Activating Token Index: 809