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

Dataset: The Pile

Neuron 1395 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8760. Min Act: -0.0000

Data Index: 132072 (The Pile)

Max Activating Token Index: 613

Text #1

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7816. Min Act: -0.0000

Data Index: 542918 (The Pile)

Max Activating Token Index: 698

Text #2

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1301707 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1568221 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6628. Min Act: -0.0000

Data Index: 313922 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1009718 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6848. Min Act: -0.0000

Data Index: 418982 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1298789 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6359. Min Act: -0.0000

Data Index: 59358 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1801717 (The Pile)

Max Activating Token Index: 30

Text #10

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6045. Min Act: -0.0000

Data Index: 854810 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1644103 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1990662 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5871. Min Act: -0.0000

Data Index: 168404 (The Pile)

Max Activating Token Index: 561

Text #14

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5876. Min Act: -0.0000

Data Index: 250706 (The Pile)

Max Activating Token Index: 290

Text #15

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5652. Min Act: -0.0000

Data Index: 41700 (The Pile)

Max Activating Token Index: 437

Text #16

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1366047 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5395. Min Act: -0.0000

Data Index: 920959 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5584. Min Act: -0.0000

Data Index: 183025 (The Pile)

Max Activating Token Index: 732

Text #19

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1686698 (The Pile)

Max Activating Token Index: 930