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

Dataset: The Pile

Neuron 3903 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.7731. Min Act: -0.0000

Data Index: 635284 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6997. Min Act: 0.0000

Data Index: 12074 (The Pile)

Max Activating Token Index: 766

Text #2

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1223317 (The Pile)

Max Activating Token Index: 904

Text #3

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1661012 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1314698 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1529740 (The Pile)

Max Activating Token Index: 20

Text #6

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6448. Min Act: -0.0000

Data Index: 740414 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6121. Min Act: -0.0000

Data Index: 373935 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1679600 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1423971 (The Pile)

Max Activating Token Index: 615

Text #10

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1291765 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6012. Min Act: -0.0000

Data Index: 219567 (The Pile)

Max Activating Token Index: 781

Text #12

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1199872 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5559. Min Act: -0.0000

Data Index: 360954 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5563. Min Act: 0.0000

Data Index: 917859 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5511. Min Act: -0.0000

Data Index: 34063 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5565. Min Act: -0.0000

Data Index: 103592 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5682. Min Act: -0.0000

Data Index: 885728 (The Pile)

Max Activating Token Index: 420

Text #18

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1703169 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5433. Min Act: -0.0000

Data Index: 615117 (The Pile)

Max Activating Token Index: 690