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

Dataset: The Pile

Neuron 1875 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.5645. Min Act: -0.0000

Data Index: 137644 (The Pile)

Max Activating Token Index: 790

Text #1

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.5283. Min Act: -0.0000

Data Index: 1300387 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4924. Min Act: -0.0000

Data Index: 553698 (The Pile)

Max Activating Token Index: 794

Text #3

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1521898 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4703. Min Act: -0.0000

Data Index: 129235 (The Pile)

Max Activating Token Index: 122

Text #5

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4628. Min Act: -0.0000

Data Index: 122003 (The Pile)

Max Activating Token Index: 7

Text #6

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1254710 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4511. Min Act: -0.0000

Data Index: 291929 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1502189 (The Pile)

Max Activating Token Index: 605

Text #9

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1121437 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1414075 (The Pile)

Max Activating Token Index: 584

Text #11

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1887992 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3958. Min Act: -0.0000

Data Index: 9662 (The Pile)

Max Activating Token Index: 351

Text #13

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1857012 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3825. Min Act: -0.0000

Data Index: 251235 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1207258 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3615. Min Act: -0.0000

Data Index: 759087 (The Pile)

Max Activating Token Index: 942

Text #17

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1880349 (The Pile)

Max Activating Token Index: 34

Text #18

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1612905 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 0.5645. Min Range: -0.5645

Max Act: 0.3799. Min Act: -0.0000

Data Index: 386962 (The Pile)

Max Activating Token Index: 370