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

Dataset: The Pile

Neuron 805 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: 1.6133. Min Range: -1.6133

Max Act: 1.6133. Min Act: -0.0000

Data Index: 1462962 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.3457. Min Act: -0.0000

Data Index: 1930917 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.2640. Min Act: -0.0000

Data Index: 987135 (The Pile)

Max Activating Token Index: 614

Text #3

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.2667. Min Act: -0.0000

Data Index: 394267 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.2221. Min Act: -0.0000

Data Index: 422430 (The Pile)

Max Activating Token Index: 306

Text #5

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0808. Min Act: -0.0000

Data Index: 626874 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.3028. Min Act: -0.0000

Data Index: 1370445 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.4127. Min Act: -0.0000

Data Index: 1790500 (The Pile)

Max Activating Token Index: 845

Text #8

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1894495 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.1966. Min Act: -0.0000

Data Index: 980939 (The Pile)

Max Activating Token Index: 841

Text #10

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1982497 (The Pile)

Max Activating Token Index: 429

Text #11

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1805718 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1648922 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.1448. Min Act: -0.0000

Data Index: 838385 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.1693. Min Act: -0.0000

Data Index: 1094099 (The Pile)

Max Activating Token Index: 853

Text #15

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.1849. Min Act: -0.0000

Data Index: 551893 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.1009. Min Act: -0.0000

Data Index: 951697 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1981801 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0764. Min Act: -0.0000

Data Index: 136692 (The Pile)

Max Activating Token Index: 685

Text #19

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1593368 (The Pile)

Max Activating Token Index: 566