Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2559 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.3782. Min Range: -3.3782

Max Act: 3.3782. Min Act: -0.0000

Data Index: 1417375 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 3.3782. Min Range: -3.3782

Max Act: 3.1157. Min Act: -0.0000

Data Index: 1084170 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 3.3782. Min Range: -3.3782

Max Act: 3.2816. Min Act: -0.0000

Data Index: 676458 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 3.3782. Min Range: -3.3782

Max Act: 3.0841. Min Act: -0.0000

Data Index: 1482416 (The Pile)

Max Activating Token Index: 864

Text #4

Max Range: 3.3782. Min Range: -3.3782

Max Act: 3.0672. Min Act: -0.0000

Data Index: 178157 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 3.3782. Min Range: -3.3782

Max Act: 3.2147. Min Act: -0.0000

Data Index: 906977 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 3.3782. Min Range: -3.3782

Max Act: 3.1080. Min Act: -0.0000

Data Index: 1567837 (The Pile)

Max Activating Token Index: 943

Text #7

Max Range: 3.3782. Min Range: -3.3782

Max Act: 3.3453. Min Act: -0.0000

Data Index: 546526 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.9663. Min Act: -0.0000

Data Index: 1661239 (The Pile)

Max Activating Token Index: 428

Text #9

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.8000. Min Act: -0.0000

Data Index: 1463751 (The Pile)

Max Activating Token Index: 762

Text #10

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.7712. Min Act: -0.0000

Data Index: 410853 (The Pile)

Max Activating Token Index: 679

Text #11

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.9199. Min Act: -0.0000

Data Index: 1605952 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.6286. Min Act: -0.0000

Data Index: 465342 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.8994. Min Act: -0.0000

Data Index: 400169 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.8753. Min Act: -0.0000

Data Index: 1455878 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.7529. Min Act: -0.0000

Data Index: 837047 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.8558. Min Act: -0.0000

Data Index: 1812901 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.8261. Min Act: -0.0000

Data Index: 1638870 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.6699. Min Act: -0.0000

Data Index: 939836 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 3.3782. Min Range: -3.3782

Max Act: 2.7909. Min Act: -0.0000

Data Index: 1302770 (The Pile)

Max Activating Token Index: 532