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

Dataset: The Pile

Neuron 3493 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1794. Min Act: -0.0000

Data Index: 971944 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1319336 (The Pile)

Max Activating Token Index: 417

Text #2

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1578942 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1544. Min Act: -0.0000

Data Index: 152190 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1334678 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1605. Min Act: -0.0000

Data Index: 912697 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1204412 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1397. Min Act: -0.0000

Data Index: 689312 (The Pile)

Max Activating Token Index: 974

Text #8

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1560705 (The Pile)

Max Activating Token Index: 319

Text #9

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1903336 (The Pile)

Max Activating Token Index: 581

Text #10

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1394. Min Act: -0.0000

Data Index: 132373 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1545. Min Act: -0.0000

Data Index: 438884 (The Pile)

Max Activating Token Index: 781

Text #12

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1372. Min Act: -0.0000

Data Index: 594511 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1656363 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1335371 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1300. Min Act: -0.0000

Data Index: 98764 (The Pile)

Max Activating Token Index: 443

Text #16

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1893476 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1315993 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1368. Min Act: -0.0000

Data Index: 129357 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1104174 (The Pile)

Max Activating Token Index: 697