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

Dataset: The Pile

Neuron 417 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: 0.1685. Min Range: -0.1685

Max Act: 0.1685. Min Act: -0.0000

Data Index: 320773 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1428428 (The Pile)

Max Activating Token Index: 727

Text #2

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1323811 (The Pile)

Max Activating Token Index: 302

Text #3

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1523. Min Act: -0.0000

Data Index: 661378 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1535. Min Act: -0.0000

Data Index: 303288 (The Pile)

Max Activating Token Index: 721

Text #5

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1510. Min Act: -0.0000

Data Index: 458300 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1626370 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1441. Min Act: 0.0000

Data Index: 1390806 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1420. Min Act: -0.0000

Data Index: 857505 (The Pile)

Max Activating Token Index: 656

Text #9

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1405. Min Act: -0.0000

Data Index: 252310 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1430533 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1162810 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1400. Min Act: -0.0000

Data Index: 272519 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1445. Min Act: -0.0000

Data Index: 623418 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1347. Min Act: -0.0000

Data Index: 53788 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1358. Min Act: -0.0000

Data Index: 1790023 (The Pile)

Max Activating Token Index: 919

Text #16

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1331. Min Act: 0.0000

Data Index: 1740535 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1432. Min Act: -0.0000

Data Index: 399998 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1908834 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1369. Min Act: -0.0000

Data Index: 308220 (The Pile)

Max Activating Token Index: 471