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

Dataset: The Pile

Neuron 380 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: 0.6762. Min Range: -0.6762

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1355461 (The Pile)

Max Activating Token Index: 490

Text #1

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1416511 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1251604 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6105. Min Act: -0.0000

Data Index: 883933 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1622912 (The Pile)

Max Activating Token Index: 859

Text #5

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5657. Min Act: -0.0000

Data Index: 510076 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1805361 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5682. Min Act: -0.0000

Data Index: 608729 (The Pile)

Max Activating Token Index: 765

Text #8

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5806. Min Act: -0.0000

Data Index: 667402 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6047. Min Act: -0.0000

Data Index: 262597 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1078448 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1191512 (The Pile)

Max Activating Token Index: 212

Text #12

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1867528 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1641130 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5973. Min Act: -0.0000

Data Index: 609 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1825384 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5534. Min Act: -0.0000

Data Index: 346868 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1299782 (The Pile)

Max Activating Token Index: 566

Text #18

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1216902 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1962938 (The Pile)

Max Activating Token Index: 744