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

Dataset: The Pile

Neuron 1792 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: 0.1505. Min Range: -0.1505

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1166041 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1402. Min Act: -0.0000

Data Index: 411595 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1582450 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1309759 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1115676 (The Pile)

Max Activating Token Index: 986

Text #5

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1210. Min Act: -0.0000

Data Index: 358772 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1188842 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1030. Min Act: -0.0000

Data Index: 302920 (The Pile)

Max Activating Token Index: 977

Text #8

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1086. Min Act: -0.0000

Data Index: 297867 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0790. Min Act: -0.0000

Data Index: 750525 (The Pile)

Max Activating Token Index: 996

Text #10

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1099581 (The Pile)

Max Activating Token Index: 792

Text #11

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1089. Min Act: -0.0000

Data Index: 506856 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1508631 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1080. Min Act: -0.0000

Data Index: 313803 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1662319 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0926. Min Act: -0.0000

Data Index: 745734 (The Pile)

Max Activating Token Index: 951

Text #16

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1614726 (The Pile)

Max Activating Token Index: 753

Text #17

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1125080 (The Pile)

Max Activating Token Index: 414

Text #18

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0934. Min Act: -0.0000

Data Index: 1867055 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1307752 (The Pile)

Max Activating Token Index: 964