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

Dataset: The Pile

Neuron 4872 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: 0.8981. Min Range: -0.8981

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1128661 (The Pile)

Max Activating Token Index: 680

Text #1

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1903521 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7607. Min Act: -0.0000

Data Index: 1795197 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7261. Min Act: -0.0000

Data Index: 69853 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7108. Min Act: -0.0000

Data Index: 213788 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7338. Min Act: -0.0000

Data Index: 933556 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1225360 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6738. Min Act: -0.0000

Data Index: 805169 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1456438 (The Pile)

Max Activating Token Index: 782

Text #9

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6955. Min Act: -0.0000

Data Index: 648542 (The Pile)

Max Activating Token Index: 371

Text #10

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6822. Min Act: -0.0000

Data Index: 904229 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7036. Min Act: -0.0000

Data Index: 345176 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1856081 (The Pile)

Max Activating Token Index: 1001

Text #13

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1148894 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1246335 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6914. Min Act: -0.0000

Data Index: 689332 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1396118 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1186765 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6485. Min Act: -0.0000

Data Index: 185554 (The Pile)

Max Activating Token Index: 927

Text #19

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6829. Min Act: -0.0000

Data Index: 147307 (The Pile)

Max Activating Token Index: 278