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

Dataset: The Pile

Neuron 581 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: 1.8892. Min Range: -1.8892

Max Act: 1.8892. Min Act: -0.0000

Data Index: 1185071 (The Pile)

Max Activating Token Index: 336

Text #1

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.8509. Min Act: -0.0000

Data Index: 814135 (The Pile)

Max Activating Token Index: 331

Text #2

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.8566. Min Act: -0.0000

Data Index: 1017859 (The Pile)

Max Activating Token Index: 273

Text #3

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.3895. Min Act: -0.0000

Data Index: 1348644 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.1399. Min Act: -0.0000

Data Index: 1518597 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1127433 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1243893 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.0357. Min Act: -0.0000

Data Index: 1977454 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 1.8892. Min Range: -1.8892

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1231365 (The Pile)

Max Activating Token Index: 973

Text #9

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.0065. Min Act: -0.0000

Data Index: 876218 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 1.8892. Min Range: -1.8892

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1409259 (The Pile)

Max Activating Token Index: 367

Text #11

Max Range: 1.8892. Min Range: -1.8892

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1634363 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 1.8892. Min Range: -1.8892

Max Act: 0.8782. Min Act: -0.0000

Data Index: 71706 (The Pile)

Max Activating Token Index: 287

Text #13

Max Range: 1.8892. Min Range: -1.8892

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1343723 (The Pile)

Max Activating Token Index: 737

Text #14

Max Range: 1.8892. Min Range: -1.8892

Max Act: 0.8744. Min Act: -0.0000

Data Index: 966347 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 1.8892. Min Range: -1.8892

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1409401 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 1.8892. Min Range: -1.8892

Max Act: 0.8600. Min Act: -0.0000

Data Index: 755722 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 1.8892. Min Range: -1.8892

Max Act: 0.8265. Min Act: -0.0000

Data Index: 627162 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 1.8892. Min Range: -1.8892

Max Act: 0.8851. Min Act: -0.0000

Data Index: 546193 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 1.8892. Min Range: -1.8892

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1576093 (The Pile)

Max Activating Token Index: 58