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

Dataset: The Pile

Neuron 3548 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: 1.2401. Min Range: -1.2401

Max Act: 1.2401. Min Act: -0.0000

Data Index: 1343249 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 1.2401. Min Range: -1.2401

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1879160 (The Pile)

Max Activating Token Index: 645

Text #2

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.9813. Min Act: -0.0000

Data Index: 219984 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.9095. Min Act: -0.0000

Data Index: 158912 (The Pile)

Max Activating Token Index: 424

Text #4

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.9074. Min Act: -0.0000

Data Index: 593124 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.9814. Min Act: -0.0000

Data Index: 555964 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.8062. Min Act: -0.0000

Data Index: 372018 (The Pile)

Max Activating Token Index: 62

Text #7

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1634392 (The Pile)

Max Activating Token Index: 964

Text #8

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.7624. Min Act: -0.0000

Data Index: 728251 (The Pile)

Max Activating Token Index: 833

Text #9

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.7305. Min Act: -0.0000

Data Index: 557054 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.6284. Min Act: -0.0000

Data Index: 536876 (The Pile)

Max Activating Token Index: 665

Text #11

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.6214. Min Act: -0.0000

Data Index: 346029 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.6785. Min Act: -0.0000

Data Index: 928687 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1609057 (The Pile)

Max Activating Token Index: 394

Text #14

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.5618. Min Act: -0.0000

Data Index: 440070 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1026042 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.6361. Min Act: -0.0000

Data Index: 181140 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.6398. Min Act: -0.0000

Data Index: 651710 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.5963. Min Act: -0.0000

Data Index: 497787 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1403700 (The Pile)

Max Activating Token Index: 713