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

Dataset: The Pile

Neuron 1744 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.5612. Min Act: -0.0000

Data Index: 309327 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.5042. Min Act: -0.0000

Data Index: 864964 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.5038. Min Act: -0.0000

Data Index: 833233 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1949591 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4674. Min Act: -0.0000

Data Index: 452605 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4682. Min Act: -0.0000

Data Index: 879242 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4698. Min Act: -0.0000

Data Index: 665349 (The Pile)

Max Activating Token Index: 883

Text #7

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4789. Min Act: -0.0000

Data Index: 284914 (The Pile)

Max Activating Token Index: 727

Text #8

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4634. Min Act: -0.0000

Data Index: 53977 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1141882 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4119. Min Act: -0.0000

Data Index: 535119 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1635382 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1381106 (The Pile)

Max Activating Token Index: 672

Text #13

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4639. Min Act: -0.0000

Data Index: 869190 (The Pile)

Max Activating Token Index: 888

Text #14

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4650. Min Act: -0.0000

Data Index: 939586 (The Pile)

Max Activating Token Index: 110

Text #15

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1791328 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1424129 (The Pile)

Max Activating Token Index: 694

Text #17

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4351. Min Act: -0.0000

Data Index: 907499 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4351. Min Act: -0.0000

Data Index: 213176 (The Pile)

Max Activating Token Index: 687

Text #19

Max Range: 0.5612. Min Range: -0.5612

Max Act: 0.4376. Min Act: -0.0000

Data Index: 273388 (The Pile)

Max Activating Token Index: 502