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

Dataset: The Pile

Neuron 5073 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: 0.1853. Min Range: -0.1853

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1008675 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1609528 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1428. Min Act: -0.0000

Data Index: 123381 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1475. Min Act: -0.0000

Data Index: 261089 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1522. Min Act: -0.0000

Data Index: 443402 (The Pile)

Max Activating Token Index: 212

Text #5

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1932417 (The Pile)

Max Activating Token Index: 594

Text #6

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1348545 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1845055 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1426. Min Act: -0.0000

Data Index: 60641 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1301696 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1394. Min Act: -0.0000

Data Index: 217195 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1406. Min Act: -0.0000

Data Index: 869139 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1317. Min Act: -0.0000

Data Index: 98410 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1543962 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1449. Min Act: -0.0000

Data Index: 496692 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1347. Min Act: -0.0000

Data Index: 186380 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1281. Min Act: -0.0000

Data Index: 44940 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1650766 (The Pile)

Max Activating Token Index: 589

Text #18

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1104373 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1300. Min Act: -0.0000

Data Index: 856010 (The Pile)

Max Activating Token Index: 607