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

Dataset: The Pile

Neuron 4711 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: 3.5393. Min Range: -3.5393

Max Act: 3.5393. Min Act: -0.0000

Data Index: 621646 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.4698. Min Act: -0.0000

Data Index: 700006 (The Pile)

Max Activating Token Index: 245

Text #2

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.4694. Min Act: -0.0000

Data Index: 341623 (The Pile)

Max Activating Token Index: 27

Text #3

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.4405. Min Act: -0.0000

Data Index: 1437970 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.4008. Min Act: -0.0000

Data Index: 1426622 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.4565. Min Act: -0.0000

Data Index: 1442693 (The Pile)

Max Activating Token Index: 655

Text #6

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.5081. Min Act: -0.0000

Data Index: 1801533 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.2931. Min Act: -0.0000

Data Index: 828576 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.2552. Min Act: -0.0000

Data Index: 61480 (The Pile)

Max Activating Token Index: 403

Text #9

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.2366. Min Act: -0.0000

Data Index: 997207 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.1890. Min Act: -0.0000

Data Index: 733192 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.1870. Min Act: -0.0000

Data Index: 1335948 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.1592. Min Act: -0.0000

Data Index: 1242386 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.1915. Min Act: -0.0000

Data Index: 1497862 (The Pile)

Max Activating Token Index: 887

Text #14

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.1197. Min Act: -0.0000

Data Index: 512090 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.1254. Min Act: -0.0000

Data Index: 1982035 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.0822. Min Act: -0.0000

Data Index: 1927794 (The Pile)

Max Activating Token Index: 7

Text #17

Max Range: 3.5393. Min Range: -3.5393

Max Act: 2.9430. Min Act: -0.0000

Data Index: 771852 (The Pile)

Max Activating Token Index: 181

Text #18

Max Range: 3.5393. Min Range: -3.5393

Max Act: 2.9580. Min Act: -0.0000

Data Index: 246069 (The Pile)

Max Activating Token Index: 902

Text #19

Max Range: 3.5393. Min Range: -3.5393

Max Act: 3.0526. Min Act: -0.0000

Data Index: 201895 (The Pile)

Max Activating Token Index: 477