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

Dataset: The Pile

Neuron 3732 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1914. Min Range: -1.1914

Max Act: 1.1914. Min Act: -0.0000

Data Index: 207771 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9087. Min Act: -0.0000

Data Index: 201287 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1995904 (The Pile)

Max Activating Token Index: 405

Text #3

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1861144 (The Pile)

Max Activating Token Index: 732

Text #4

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1423044 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1566941 (The Pile)

Max Activating Token Index: 35

Text #6

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8144. Min Act: -0.0000

Data Index: 933645 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1453573 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1098839 (The Pile)

Max Activating Token Index: 977

Text #9

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1362091 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1670582 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7649. Min Act: -0.0000

Data Index: 870355 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7783. Min Act: -0.0000

Data Index: 365909 (The Pile)

Max Activating Token Index: 907

Text #13

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7575. Min Act: -0.0000

Data Index: 633684 (The Pile)

Max Activating Token Index: 373

Text #14

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1917137 (The Pile)

Max Activating Token Index: 740

Text #15

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1369865 (The Pile)

Max Activating Token Index: 881

Text #16

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1702679 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1903920 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7291. Min Act: -0.0000

Data Index: 379126 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1480574 (The Pile)

Max Activating Token Index: 43