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

Dataset: The Pile

Neuron 52 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.2797. Min Act: -0.0000

Data Index: 55634 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.1886. Min Act: -0.0000

Data Index: 754565 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0985. Min Act: -0.0000

Data Index: 1822950 (The Pile)

Max Activating Token Index: 799

Text #3

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0760. Min Act: 0.0000

Data Index: 363696 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0475. Min Act: -0.0000

Data Index: 1442344 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.1758. Min Act: -0.0000

Data Index: 483583 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9968. Min Act: -0.0000

Data Index: 1521685 (The Pile)

Max Activating Token Index: 959

Text #7

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0138. Min Act: -0.0000

Data Index: 1531765 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0115. Min Act: -0.0000

Data Index: 1271733 (The Pile)

Max Activating Token Index: 720

Text #9

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9778. Min Act: -0.0000

Data Index: 1142140 (The Pile)

Max Activating Token Index: 974

Text #10

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.8251. Min Act: -0.0000

Data Index: 1922719 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9610. Min Act: -0.0000

Data Index: 1828510 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9391. Min Act: -0.0000

Data Index: 1464162 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9486. Min Act: -0.0000

Data Index: 1740002 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0880. Min Act: -0.0000

Data Index: 652791 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9425. Min Act: -0.0000

Data Index: 1564531 (The Pile)

Max Activating Token Index: 455

Text #16

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9162. Min Act: -0.0000

Data Index: 901638 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9231. Min Act: -0.0000

Data Index: 656871 (The Pile)

Max Activating Token Index: 336

Text #18

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.8884. Min Act: -0.0000

Data Index: 110032 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.8762. Min Act: -0.0000

Data Index: 356668 (The Pile)

Max Activating Token Index: 327