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

Dataset: The Pile

Neuron 3654 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: 1.6359. Min Range: -1.6359

Max Act: 1.5812. Min Act: -0.0000

Data Index: 1684154 (The Pile)

Max Activating Token Index: 635

Text #1

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.4600. Min Act: -0.0000

Data Index: 980157 (The Pile)

Max Activating Token Index: 783

Text #2

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.6359. Min Act: -0.0000

Data Index: 633547 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.3331. Min Act: -0.0000

Data Index: 1311943 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.2387. Min Act: -0.0000

Data Index: 1328568 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.3174. Min Act: -0.0000

Data Index: 1491087 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1508840 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.3628. Min Act: -0.0000

Data Index: 731378 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1305688 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.0457. Min Act: -0.0000

Data Index: 735130 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.1769. Min Act: -0.0000

Data Index: 609430 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.1609. Min Act: -0.0000

Data Index: 523960 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.1589. Min Act: -0.0000

Data Index: 936819 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.1062. Min Act: -0.0000

Data Index: 1359710 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.1466. Min Act: -0.0000

Data Index: 361959 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.1241. Min Act: -0.0000

Data Index: 133052 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1140122 (The Pile)

Max Activating Token Index: 529

Text #17

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.0301. Min Act: -0.0000

Data Index: 839990 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 1.6359. Min Range: -1.6359

Max Act: 1.0671. Min Act: -0.0000

Data Index: 682377 (The Pile)

Max Activating Token Index: 481

Text #19

Max Range: 1.6359. Min Range: -1.6359

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1567194 (The Pile)

Max Activating Token Index: 587