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

Dataset: The Pile

Neuron 3549 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: 0.2148. Min Range: -0.2148

Max Act: 0.2148. Min Act: -0.0000

Data Index: 191358 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.2092. Min Act: 0.0000

Data Index: 1900009 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1956. Min Act: -0.0000

Data Index: 106505 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.2017. Min Act: -0.0000

Data Index: 139136 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1585983 (The Pile)

Max Activating Token Index: 270

Text #5

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1867. Min Act: -0.0000

Data Index: 394908 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1727. Min Act: -0.0000

Data Index: 47703 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1827490 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1896. Min Act: -0.0000

Data Index: 272907 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1939974 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1517860 (The Pile)

Max Activating Token Index: 280

Text #11

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1578. Min Act: -0.0000

Data Index: 908034 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1608893 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1799742 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1660612 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1089145 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1533. Min Act: -0.0000

Data Index: 793318 (The Pile)

Max Activating Token Index: 20

Text #17

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1897339 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1602822 (The Pile)

Max Activating Token Index: 756

Text #19

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1389323 (The Pile)

Max Activating Token Index: 403