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

Dataset: The Pile

Neuron 1097 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: 1.4414. Min Range: -1.4414

Max Act: 1.4414. Min Act: -0.0000

Data Index: 1713480 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.1694. Min Act: -0.0000

Data Index: 982095 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1648583 (The Pile)

Max Activating Token Index: 636

Text #3

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.0189. Min Act: -0.0000

Data Index: 238152 (The Pile)

Max Activating Token Index: 902

Text #4

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1924413 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1199577 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1557622 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1826091 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.8347. Min Act: -0.0000

Data Index: 373691 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1135189 (The Pile)

Max Activating Token Index: 966

Text #10

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1136493 (The Pile)

Max Activating Token Index: 706

Text #11

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1712881 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.7670. Min Act: -0.0000

Data Index: 374039 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1762797 (The Pile)

Max Activating Token Index: 780

Text #14

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.7999. Min Act: -0.0000

Data Index: 243092 (The Pile)

Max Activating Token Index: 999

Text #15

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1109052 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1129475 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.6895. Min Act: -0.0000

Data Index: 213822 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.6865. Min Act: -0.0000

Data Index: 834773 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 1.4414. Min Range: -1.4414

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1819520 (The Pile)

Max Activating Token Index: 677