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

Dataset: The Pile

Neuron 1927 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: 0.7765. Min Range: -0.7765

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1894383 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7765. Min Act: 0.0000

Data Index: 1189423 (The Pile)

Max Activating Token Index: 88

Text #2

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7339. Min Act: -0.0000

Data Index: 909093 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6589. Min Act: -0.0000

Data Index: 361655 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7578. Min Act: 0.0000

Data Index: 753949 (The Pile)

Max Activating Token Index: 122

Text #5

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1791412 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1985534 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6531. Min Act: 0.0000

Data Index: 384938 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6952. Min Act: -0.0000

Data Index: 505143 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6895. Min Act: -0.0000

Data Index: 883253 (The Pile)

Max Activating Token Index: 45

Text #10

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1855507 (The Pile)

Max Activating Token Index: 104

Text #11

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6594. Min Act: -0.0000

Data Index: 888820 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6638. Min Act: -0.0000

Data Index: 817728 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1631684 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7035. Min Act: -0.0000

Data Index: 54687 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7187. Min Act: -0.0000

Data Index: 662918 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1908752 (The Pile)

Max Activating Token Index: 518

Text #17

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1444745 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1439306 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6395. Min Act: -0.0000

Data Index: 600224 (The Pile)

Max Activating Token Index: 830