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

Dataset: The Pile

Neuron 3835 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: 1.5995. Min Range: -1.5995

Max Act: 1.5995. Min Act: -0.0000

Data Index: 625627 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.4299. Min Act: -0.0000

Data Index: 527591 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1155359 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.0641. Min Act: -0.0000

Data Index: 422968 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1779944 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1323775 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1108 (The Pile)

Max Activating Token Index: 228

Text #7

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1915073 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8971. Min Act: -0.0000

Data Index: 36233 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1789894 (The Pile)

Max Activating Token Index: 484

Text #10

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1468181 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1024322 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1007733 (The Pile)

Max Activating Token Index: 280

Text #13

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9064. Min Act: -0.0000

Data Index: 793796 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8515. Min Act: -0.0000

Data Index: 781751 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1505713 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8412. Min Act: -0.0000

Data Index: 488477 (The Pile)

Max Activating Token Index: 711

Text #17

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1722510 (The Pile)

Max Activating Token Index: 966

Text #18

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8843. Min Act: -0.0000

Data Index: 882274 (The Pile)

Max Activating Token Index: 727

Text #19

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8301. Min Act: -0.0000

Data Index: 797831 (The Pile)

Max Activating Token Index: 41