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

Dataset: The Pile

Neuron 2690 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: 0.1816. Min Range: -0.1816

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1867281 (The Pile)

Max Activating Token Index: 609

Text #1

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1678523 (The Pile)

Max Activating Token Index: 974

Text #2

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1806856 (The Pile)

Max Activating Token Index: 709

Text #3

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1697. Min Act: -0.0000

Data Index: 924900 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1779021 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1082438 (The Pile)

Max Activating Token Index: 571

Text #6

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1289055 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1333. Min Act: -0.0000

Data Index: 506810 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1435. Min Act: -0.0000

Data Index: 907920 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1383. Min Act: -0.0000

Data Index: 616229 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1335. Min Act: -0.0000

Data Index: 158588 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1309. Min Act: -0.0000

Data Index: 845033 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1458563 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1273. Min Act: -0.0000

Data Index: 795775 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1303. Min Act: -0.0000

Data Index: 330666 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1455843 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1589443 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1169. Min Act: -0.0000

Data Index: 427953 (The Pile)

Max Activating Token Index: 758

Text #18

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1223. Min Act: -0.0000

Data Index: 308651 (The Pile)

Max Activating Token Index: 860

Text #19

Max Range: 0.1816. Min Range: -0.1816

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1855028 (The Pile)

Max Activating Token Index: 484