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

Dataset: The Pile

Neuron 1768 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1371704 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1806868 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1628048 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1383510 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1775. Min Act: -0.0000

Data Index: 145014 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1834371 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1946601 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1624222 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1973380 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1100905 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1532. Min Act: -0.0000

Data Index: 972129 (The Pile)

Max Activating Token Index: 909

Text #11

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1618. Min Act: -0.0000

Data Index: 706200 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1437. Min Act: -0.0000

Data Index: 583306 (The Pile)

Max Activating Token Index: 1013

Text #13

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1558. Min Act: -0.0000

Data Index: 908921 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1506. Min Act: -0.0000

Data Index: 645365 (The Pile)

Max Activating Token Index: 919

Text #15

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1612. Min Act: -0.0000

Data Index: 594353 (The Pile)

Max Activating Token Index: 904

Text #16

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1389. Min Act: -0.0000

Data Index: 292670 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1600. Min Act: -0.0000

Data Index: 315467 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1561. Min Act: -0.0000

Data Index: 124059 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1463496 (The Pile)

Max Activating Token Index: 964