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

Dataset: The Pile

Neuron 572 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.7573. Min Act: -0.0000

Data Index: 637972 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.5647. Min Act: -0.0000

Data Index: 1535068 (The Pile)

Max Activating Token Index: 471

Text #2

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.6865. Min Act: -0.0000

Data Index: 813575 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.4264. Min Act: -0.0000

Data Index: 180599 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.2778. Min Act: -0.0000

Data Index: 1807167 (The Pile)

Max Activating Token Index: 922

Text #5

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1460224 (The Pile)

Max Activating Token Index: 667

Text #6

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.1441. Min Act: -0.0000

Data Index: 121925 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1791046 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.0217. Min Act: -0.0000

Data Index: 381132 (The Pile)

Max Activating Token Index: 888

Text #9

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.1074. Min Act: -0.0000

Data Index: 95554 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.1702. Min Act: -0.0000

Data Index: 1225430 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 1.7573. Min Range: -1.7573

Max Act: 0.9455. Min Act: -0.0000

Data Index: 313928 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.1745. Min Act: -0.0000

Data Index: 271961 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.0459. Min Act: -0.0000

Data Index: 315722 (The Pile)

Max Activating Token Index: 992

Text #14

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.1245. Min Act: -0.0000

Data Index: 151380 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 1.7573. Min Range: -1.7573

Max Act: 0.9896. Min Act: -0.0000

Data Index: 723215 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 1.7573. Min Range: -1.7573

Max Act: 1.1310. Min Act: -0.0000

Data Index: 270100 (The Pile)

Max Activating Token Index: 376

Text #17

Max Range: 1.7573. Min Range: -1.7573

Max Act: 0.9130. Min Act: -0.0000

Data Index: 128077 (The Pile)

Max Activating Token Index: 968

Text #18

Max Range: 1.7573. Min Range: -1.7573

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1403056 (The Pile)

Max Activating Token Index: 956

Text #19

Max Range: 1.7573. Min Range: -1.7573

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1034371 (The Pile)

Max Activating Token Index: 1016