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

Dataset: The Pile

Neuron 2291 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: 0.4539. Min Range: -0.4539

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1398215 (The Pile)

Max Activating Token Index: 484

Text #1

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1260648 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1953792 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1667558 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3983. Min Act: 0.0000

Data Index: 1018942 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3949. Min Act: 0.0000

Data Index: 1051816 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3816. Min Act: 0.0000

Data Index: 853393 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3904. Min Act: -0.0000

Data Index: 217227 (The Pile)

Max Activating Token Index: 751

Text #8

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3413. Min Act: -0.0000

Data Index: 110572 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1528723 (The Pile)

Max Activating Token Index: 460

Text #10

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1050583 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3732. Min Act: -0.0000

Data Index: 881146 (The Pile)

Max Activating Token Index: 940

Text #12

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1487480 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3616. Min Act: -0.0000

Data Index: 402271 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1908244 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3736. Min Act: -0.0000

Data Index: 334740 (The Pile)

Max Activating Token Index: 971

Text #16

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3644. Min Act: 0.0000

Data Index: 1563784 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3541. Min Act: 0.0000

Data Index: 1789655 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3538. Min Act: 0.0000

Data Index: 375174 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1822060 (The Pile)

Max Activating Token Index: 558