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

Dataset: The Pile

Neuron 3604 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: 5.3918. Min Range: -5.3918

Max Act: 5.3918. Min Act: -0.0000

Data Index: 1494357 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 5.3918. Min Range: -5.3918

Max Act: 4.5606. Min Act: -0.0000

Data Index: 1417041 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 5.3918. Min Range: -5.3918

Max Act: 4.9327. Min Act: -0.0000

Data Index: 1837714 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 5.3918. Min Range: -5.3918

Max Act: 5.0810. Min Act: -0.0000

Data Index: 436425 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 5.3918. Min Range: -5.3918

Max Act: 4.1134. Min Act: -0.0000

Data Index: 210914 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 5.3918. Min Range: -5.3918

Max Act: 4.8881. Min Act: -0.0000

Data Index: 1127512 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 5.3918. Min Range: -5.3918

Max Act: 4.2418. Min Act: -0.0000

Data Index: 677820 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 5.3918. Min Range: -5.3918

Max Act: 4.0738. Min Act: -0.0000

Data Index: 1924335 (The Pile)

Max Activating Token Index: 277

Text #8

Max Range: 5.3918. Min Range: -5.3918

Max Act: 4.0578. Min Act: 0.0001

Data Index: 374939 (The Pile)

Max Activating Token Index: 954

Text #9

Max Range: 5.3918. Min Range: -5.3918

Max Act: 4.0037. Min Act: 0.0001

Data Index: 1028081 (The Pile)

Max Activating Token Index: 832

Text #10

Max Range: 5.3918. Min Range: -5.3918

Max Act: 3.8581. Min Act: -0.0000

Data Index: 1074185 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 5.3918. Min Range: -5.3918

Max Act: 3.5933. Min Act: -0.0000

Data Index: 341021 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 5.3918. Min Range: -5.3918

Max Act: 3.6599. Min Act: -0.0000

Data Index: 1287027 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 5.3918. Min Range: -5.3918

Max Act: 3.9061. Min Act: -0.0000

Data Index: 66695 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 5.3918. Min Range: -5.3918

Max Act: 3.6022. Min Act: -0.0000

Data Index: 1584941 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 5.3918. Min Range: -5.3918

Max Act: 3.7006. Min Act: -0.0000

Data Index: 701250 (The Pile)

Max Activating Token Index: 641

Text #16

Max Range: 5.3918. Min Range: -5.3918

Max Act: 3.5768. Min Act: -0.0000

Data Index: 84179 (The Pile)

Max Activating Token Index: 261

Text #17

Max Range: 5.3918. Min Range: -5.3918

Max Act: 3.8658. Min Act: 0.0000

Data Index: 671790 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 5.3918. Min Range: -5.3918

Max Act: 3.5072. Min Act: 0.0001

Data Index: 1930128 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 5.3918. Min Range: -5.3918

Max Act: 3.6486. Min Act: 0.0000

Data Index: 1266868 (The Pile)

Max Activating Token Index: 263