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

Dataset: The Pile

Neuron 1239 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: 0.1614. Min Range: -0.1614

Max Act: 0.1614. Min Act: -0.0000

Data Index: 746149 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1507. Min Act: -0.0000

Data Index: 631684 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1271. Min Act: -0.0000

Data Index: 620339 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1962070 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0650. Min Act: -0.0000

Data Index: 444458 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0655. Min Act: -0.0000

Data Index: 653446 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0673. Min Act: -0.0000

Data Index: 79080 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1565260 (The Pile)

Max Activating Token Index: 356

Text #8

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0603. Min Act: -0.0000

Data Index: 1996072 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0557. Min Act: -0.0000

Data Index: 706607 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1684080 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0552. Min Act: -0.0000

Data Index: 984460 (The Pile)

Max Activating Token Index: 249

Text #12

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1788933 (The Pile)

Max Activating Token Index: 907

Text #13

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0672. Min Act: -0.0000

Data Index: 153506 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0601. Min Act: -0.0000

Data Index: 249860 (The Pile)

Max Activating Token Index: 625

Text #15

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1996115 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0569. Min Act: -0.0000

Data Index: 634037 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0506. Min Act: -0.0000

Data Index: 706163 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0584. Min Act: -0.0000

Data Index: 459267 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1781123 (The Pile)

Max Activating Token Index: 933