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

Dataset: The Pile

Neuron 24 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.2992. Min Act: -0.0000

Data Index: 1995133 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.1420. Min Act: -0.0000

Data Index: 624559 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.1203. Min Act: -0.0000

Data Index: 1774603 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.2253. Min Act: -0.0000

Data Index: 1921748 (The Pile)

Max Activating Token Index: 17

Text #4

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.1299. Min Act: -0.0000

Data Index: 266227 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.1388. Min Act: -0.0000

Data Index: 750195 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0971. Min Act: -0.0000

Data Index: 794982 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1832139 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.1223. Min Act: -0.0000

Data Index: 88977 (The Pile)

Max Activating Token Index: 948

Text #9

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0308. Min Act: -0.0000

Data Index: 1121243 (The Pile)

Max Activating Token Index: 101

Text #10

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0618. Min Act: -0.0000

Data Index: 277179 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0245. Min Act: -0.0000

Data Index: 1409141 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1360305 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0778. Min Act: -0.0000

Data Index: 843702 (The Pile)

Max Activating Token Index: 927

Text #14

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1749107 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0120. Min Act: -0.0000

Data Index: 837193 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.9608. Min Act: -0.0000

Data Index: 662456 (The Pile)

Max Activating Token Index: 234

Text #17

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1504576 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0400. Min Act: -0.0000

Data Index: 462258 (The Pile)

Max Activating Token Index: 688

Text #19

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.9888. Min Act: -0.0000

Data Index: 256189 (The Pile)

Max Activating Token Index: 577