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

Dataset: The Pile

Neuron 709 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: 1.8731. Min Range: -1.8731

Max Act: 1.8731. Min Act: -0.0000

Data Index: 861769 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.7826. Min Act: -0.0000

Data Index: 122963 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.7412. Min Act: -0.0000

Data Index: 270275 (The Pile)

Max Activating Token Index: 611

Text #3

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.8263. Min Act: -0.0000

Data Index: 955286 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.6889. Min Act: -0.0000

Data Index: 1582617 (The Pile)

Max Activating Token Index: 353

Text #5

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.7341. Min Act: -0.0000

Data Index: 1366219 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.5046. Min Act: -0.0000

Data Index: 1735799 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.4950. Min Act: -0.0000

Data Index: 1876107 (The Pile)

Max Activating Token Index: 737

Text #8

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.5602. Min Act: -0.0000

Data Index: 218945 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.5209. Min Act: -0.0000

Data Index: 1998023 (The Pile)

Max Activating Token Index: 623

Text #10

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.4188. Min Act: -0.0000

Data Index: 1537401 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.4936. Min Act: -0.0000

Data Index: 768165 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.4882. Min Act: -0.0000

Data Index: 1050657 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.4819. Min Act: -0.0000

Data Index: 1734719 (The Pile)

Max Activating Token Index: 715

Text #14

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.5667. Min Act: -0.0000

Data Index: 1654849 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.4740. Min Act: -0.0000

Data Index: 1475643 (The Pile)

Max Activating Token Index: 31

Text #16

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.4524. Min Act: -0.0000

Data Index: 1744208 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.4369. Min Act: -0.0000

Data Index: 1285601 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.5077. Min Act: -0.0000

Data Index: 1935783 (The Pile)

Max Activating Token Index: 342

Text #19

Max Range: 1.8731. Min Range: -1.8731

Max Act: 1.3355. Min Act: -0.0000

Data Index: 1478503 (The Pile)

Max Activating Token Index: 506