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

Dataset: The Pile

Neuron 877 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.9194. Min Act: -0.0000

Data Index: 1013073 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 4.1582. Min Range: -4.1582

Max Act: 4.1582. Min Act: -0.0000

Data Index: 651670 (The Pile)

Max Activating Token Index: 844

Text #2

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.9502. Min Act: -0.0000

Data Index: 1887515 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.8886. Min Act: -0.0000

Data Index: 564283 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.8608. Min Act: -0.0000

Data Index: 82647 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.5508. Min Act: -0.0000

Data Index: 704357 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.3436. Min Act: -0.0000

Data Index: 1212623 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.2750. Min Act: -0.0000

Data Index: 445477 (The Pile)

Max Activating Token Index: 491

Text #8

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.0647. Min Act: -0.0000

Data Index: 1079181 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.4719. Min Act: -0.0000

Data Index: 1365883 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.9813. Min Act: -0.0000

Data Index: 321378 (The Pile)

Max Activating Token Index: 329

Text #11

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.3533. Min Act: -0.0000

Data Index: 689394 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.9320. Min Act: -0.0000

Data Index: 299092 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.0205. Min Act: -0.0000

Data Index: 258923 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.7436. Min Act: -0.0000

Data Index: 1127693 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.7548. Min Act: -0.0000

Data Index: 1932108 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.8262. Min Act: -0.0000

Data Index: 1220453 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.6609. Min Act: -0.0000

Data Index: 1569420 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.5447. Min Act: -0.0000

Data Index: 1367332 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.7607. Min Act: -0.0000

Data Index: 842218 (The Pile)

Max Activating Token Index: 725