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

Dataset: The Pile

Neuron 1677 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1606860 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2191. Min Act: -0.0000

Data Index: 63722 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1675012 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1059440 (The Pile)

Max Activating Token Index: 551

Text #4

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1248547 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1957164 (The Pile)

Max Activating Token Index: 83

Text #6

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1794. Min Act: -0.0000

Data Index: 531787 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1763. Min Act: -0.0000

Data Index: 360397 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1622. Min Act: -0.0000

Data Index: 588189 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1558. Min Act: -0.0000

Data Index: 258575 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1493. Min Act: -0.0000

Data Index: 942561 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1191666 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1566. Min Act: -0.0000

Data Index: 804488 (The Pile)

Max Activating Token Index: 749

Text #13

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1633. Min Act: -0.0000

Data Index: 50734 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1458. Min Act: -0.0000

Data Index: 277400 (The Pile)

Max Activating Token Index: 242

Text #15

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1249317 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1573. Min Act: -0.0000

Data Index: 648480 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1383. Min Act: -0.0000

Data Index: 917156 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1323478 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1163824 (The Pile)

Max Activating Token Index: 242