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

Dataset: The Pile

Neuron 4709 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1531. Min Act: -0.0000

Data Index: 995448 (The Pile)

Max Activating Token Index: 870

Text #1

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.2945. Min Act: -0.0000

Data Index: 720215 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1377. Min Act: -0.0000

Data Index: 1286213 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1756. Min Act: -0.0000

Data Index: 873735 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1446640 (The Pile)

Max Activating Token Index: 853

Text #5

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1552. Min Act: -0.0000

Data Index: 335510 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1530. Min Act: -0.0000

Data Index: 170386 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1680541 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1738760 (The Pile)

Max Activating Token Index: 835

Text #9

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0205. Min Act: -0.0000

Data Index: 1388632 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0023. Min Act: -0.0000

Data Index: 63088 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1086639 (The Pile)

Max Activating Token Index: 365

Text #12

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0613. Min Act: -0.0000

Data Index: 906858 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9792. Min Act: -0.0000

Data Index: 224778 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1083. Min Act: -0.0000

Data Index: 1253179 (The Pile)

Max Activating Token Index: 78

Text #15

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0378. Min Act: -0.0000

Data Index: 486580 (The Pile)

Max Activating Token Index: 258

Text #16

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1984505 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1632853 (The Pile)

Max Activating Token Index: 663

Text #18

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1992656 (The Pile)

Max Activating Token Index: 835

Text #19

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1487583 (The Pile)

Max Activating Token Index: 994