Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1884 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1387850 (The Pile)

Max Activating Token Index: 778

Text #1

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1934. Min Act: -0.0000

Data Index: 522322 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1886786 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1911062 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1794956 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1517. Min Act: -0.0000

Data Index: 216603 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1463. Min Act: -0.0000

Data Index: 353673 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1701. Min Act: -0.0000

Data Index: 45623 (The Pile)

Max Activating Token Index: 702

Text #8

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1300916 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1489. Min Act: -0.0000

Data Index: 148008 (The Pile)

Max Activating Token Index: 696

Text #10

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1528. Min Act: -0.0000

Data Index: 789824 (The Pile)

Max Activating Token Index: 847

Text #11

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1472. Min Act: -0.0000

Data Index: 44687 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1538. Min Act: -0.0000

Data Index: 683072 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1383. Min Act: -0.0000

Data Index: 171574 (The Pile)

Max Activating Token Index: 749

Text #14

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1724655 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1862899 (The Pile)

Max Activating Token Index: 603

Text #16

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1264846 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1446. Min Act: -0.0000

Data Index: 896510 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1562970 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1796508 (The Pile)

Max Activating Token Index: 821