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

Dataset: The Pile

Neuron 1622 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: 1.9100. Min Range: -1.9100

Max Act: 1.9100. Min Act: -0.0000

Data Index: 497293 (The Pile)

Max Activating Token Index: 734

Text #1

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.2446. Min Act: -0.0000

Data Index: 1674558 (The Pile)

Max Activating Token Index: 279

Text #2

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.1722. Min Act: -0.0000

Data Index: 18117 (The Pile)

Max Activating Token Index: 380

Text #3

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1976769 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1709443 (The Pile)

Max Activating Token Index: 340

Text #5

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1439512 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.8678. Min Act: -0.0000

Data Index: 609393 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1561710 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1596340 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1932023 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1649871 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1248752 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.7303. Min Act: -0.0000

Data Index: 791808 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.6654. Min Act: -0.0000

Data Index: 534728 (The Pile)

Max Activating Token Index: 688

Text #14

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.6970. Min Act: -0.0000

Data Index: 109915 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.7177. Min Act: 0.0001

Data Index: 1897520 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1155357 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.7050. Min Act: -0.0000

Data Index: 330468 (The Pile)

Max Activating Token Index: 844

Text #18

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.6977. Min Act: -0.0000

Data Index: 24131 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 1.9100. Min Range: -1.9100

Max Act: 0.6797. Min Act: -0.0000

Data Index: 773245 (The Pile)

Max Activating Token Index: 140