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

Dataset: The Pile

Neuron 57 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1044654 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1099. Min Act: -0.0000

Data Index: 469622 (The Pile)

Max Activating Token Index: 449

Text #2

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1615042 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1973953 (The Pile)

Max Activating Token Index: 58

Text #4

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1814226 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1988790 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1211930 (The Pile)

Max Activating Token Index: 830

Text #7

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1480681 (The Pile)

Max Activating Token Index: 426

Text #8

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1593649 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1552730 (The Pile)

Max Activating Token Index: 662

Text #10

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1688085 (The Pile)

Max Activating Token Index: 902

Text #11

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0911. Min Act: -0.0000

Data Index: 511614 (The Pile)

Max Activating Token Index: 435

Text #12

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1026. Min Act: -0.0000

Data Index: 750364 (The Pile)

Max Activating Token Index: 144

Text #13

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1032. Min Act: -0.0000

Data Index: 622907 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0921. Min Act: -0.0000

Data Index: 675177 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1886239 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0897. Min Act: -0.0000

Data Index: 432481 (The Pile)

Max Activating Token Index: 677

Text #17

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1280200 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0870. Min Act: -0.0000

Data Index: 897474 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1918343 (The Pile)

Max Activating Token Index: 999