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

Dataset: The Pile

Neuron 1777 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.7416. Min Act: 0.0000

Data Index: 1093277 (The Pile)

Max Activating Token Index: 849

Text #1

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.7393. Min Act: -0.0000

Data Index: 153969 (The Pile)

Max Activating Token Index: 905

Text #2

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.6149. Min Act: -0.0000

Data Index: 391031 (The Pile)

Max Activating Token Index: 721

Text #3

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4407. Min Act: -0.0000

Data Index: 967928 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.7929. Min Act: -0.0000

Data Index: 804424 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.7405. Min Act: -0.0000

Data Index: 1118463 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4509. Min Act: 0.0000

Data Index: 1314508 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.3324. Min Act: -0.0000

Data Index: 1840667 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4644. Min Act: -0.0000

Data Index: 702241 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4510. Min Act: -0.0000

Data Index: 418956 (The Pile)

Max Activating Token Index: 967

Text #10

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.7957. Min Act: -0.0000

Data Index: 1854619 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4430. Min Act: 0.0000

Data Index: 791949 (The Pile)

Max Activating Token Index: 686

Text #12

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.7554. Min Act: -0.0000

Data Index: 1783632 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4366. Min Act: -0.0000

Data Index: 1279032 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5838. Min Act: -0.0000

Data Index: 1758117 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5022. Min Act: -0.0000

Data Index: 481889 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.6715. Min Act: -0.0000

Data Index: 701017 (The Pile)

Max Activating Token Index: 661

Text #17

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.3343. Min Act: -0.0000

Data Index: 364204 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4634. Min Act: -0.0000

Data Index: 1059663 (The Pile)

Max Activating Token Index: 550

Text #19

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4400. Min Act: -0.0000

Data Index: 13206 (The Pile)

Max Activating Token Index: 622