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

Dataset: The Pile

Neuron 5000 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: 0.2071. Min Range: -0.2071

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1849693 (The Pile)

Max Activating Token Index: 17

Text #1

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.2071. Min Act: -0.0000

Data Index: 969085 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1913. Min Act: -0.0000

Data Index: 571959 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1689. Min Act: -0.0000

Data Index: 177214 (The Pile)

Max Activating Token Index: 356

Text #4

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1621. Min Act: -0.0000

Data Index: 896359 (The Pile)

Max Activating Token Index: 129

Text #5

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1715. Min Act: -0.0000

Data Index: 882465 (The Pile)

Max Activating Token Index: 502

Text #6

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1513. Min Act: -0.0000

Data Index: 742313 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1168110 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1575. Min Act: -0.0000

Data Index: 710161 (The Pile)

Max Activating Token Index: 483

Text #9

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1667420 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1421. Min Act: -0.0000

Data Index: 18357 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1497. Min Act: -0.0000

Data Index: 505634 (The Pile)

Max Activating Token Index: 47

Text #12

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1552. Min Act: -0.0000

Data Index: 249753 (The Pile)

Max Activating Token Index: 514

Text #13

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1692998 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1261. Min Act: -0.0000

Data Index: 554234 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1418162 (The Pile)

Max Activating Token Index: 973

Text #16

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1255666 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1915542 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1702885 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1395. Min Act: -0.0000

Data Index: 44205 (The Pile)

Max Activating Token Index: 20