Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2233 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.6900. Min Act: -0.0000

Data Index: 1230855 (The Pile)

Max Activating Token Index: 12

Text #1

Max Range: 3.6900. Min Range: -3.6900

Max Act: 3.0573. Min Act: -0.0000

Data Index: 837848 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.6561. Min Act: -0.0000

Data Index: 1887280 (The Pile)

Max Activating Token Index: 17

Text #3

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.4227. Min Act: -0.0000

Data Index: 1878061 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.0885. Min Act: -0.0000

Data Index: 1047373 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.2338. Min Act: -0.0000

Data Index: 770821 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.1466. Min Act: -0.0000

Data Index: 300937 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.0373. Min Act: -0.0000

Data Index: 1012213 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 3.6900. Min Range: -3.6900

Max Act: 1.9716. Min Act: -0.0000

Data Index: 472090 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.0669. Min Act: -0.0000

Data Index: 1515342 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.0079. Min Act: -0.0000

Data Index: 883356 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 3.6900. Min Range: -3.6900

Max Act: 1.9554. Min Act: -0.0000

Data Index: 52216 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.0763. Min Act: -0.0000

Data Index: 539678 (The Pile)

Max Activating Token Index: 14

Text #13

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.0818. Min Act: -0.0000

Data Index: 342094 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 3.6900. Min Range: -3.6900

Max Act: 1.9026. Min Act: -0.0000

Data Index: 980909 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 3.6900. Min Range: -3.6900

Max Act: 1.9989. Min Act: -0.0000

Data Index: 1367570 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 3.6900. Min Range: -3.6900

Max Act: 1.8926. Min Act: -0.0000

Data Index: 1019950 (The Pile)

Max Activating Token Index: 13

Text #17

Max Range: 3.6900. Min Range: -3.6900

Max Act: 1.7787. Min Act: -0.0000

Data Index: 233920 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 3.6900. Min Range: -3.6900

Max Act: 2.0814. Min Act: -0.0000

Data Index: 942792 (The Pile)

Max Activating Token Index: 727

Text #19

Max Range: 3.6900. Min Range: -3.6900

Max Act: 1.9154. Min Act: -0.0000

Data Index: 1638507 (The Pile)

Max Activating Token Index: 171