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

Dataset: The Pile

Neuron 5005 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: 1.1723. Min Range: -1.1723

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1351892 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 1.1723. Min Range: -1.1723

Max Act: 1.1723. Min Act: -0.0000

Data Index: 986145 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 1.1723. Min Range: -1.1723

Max Act: 1.0498. Min Act: -0.0000

Data Index: 854279 (The Pile)

Max Activating Token Index: 713

Text #3

Max Range: 1.1723. Min Range: -1.1723

Max Act: 1.0872. Min Act: -0.0000

Data Index: 1784538 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 1.1723. Min Range: -1.1723

Max Act: 1.0661. Min Act: -0.0000

Data Index: 396635 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 1.1723. Min Range: -1.1723

Max Act: 1.0352. Min Act: -0.0000

Data Index: 230227 (The Pile)

Max Activating Token Index: 821

Text #6

Max Range: 1.1723. Min Range: -1.1723

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1001422 (The Pile)

Max Activating Token Index: 727

Text #7

Max Range: 1.1723. Min Range: -1.1723

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1840017 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 1.1723. Min Range: -1.1723

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1012434 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9368. Min Act: -0.0000

Data Index: 657265 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1706609 (The Pile)

Max Activating Token Index: 814

Text #11

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9243. Min Act: -0.0000

Data Index: 860815 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9896. Min Act: -0.0000

Data Index: 160943 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1400081 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1501932 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9522. Min Act: -0.0000

Data Index: 818769 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9102. Min Act: -0.0000

Data Index: 572984 (The Pile)

Max Activating Token Index: 177

Text #17

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9356. Min Act: -0.0000

Data Index: 279870 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9365. Min Act: -0.0000

Data Index: 118167 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1326644 (The Pile)

Max Activating Token Index: 363