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

Dataset: The Pile

Neuron 5113 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1720111 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.2983. Min Act: 0.0000

Data Index: 571618 (The Pile)

Max Activating Token Index: 331

Text #2

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.3432. Min Act: -0.0000

Data Index: 592904 (The Pile)

Max Activating Token Index: 389

Text #3

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1812. Min Act: 0.0000

Data Index: 1751102 (The Pile)

Max Activating Token Index: 674

Text #4

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0758. Min Act: -0.0000

Data Index: 1250454 (The Pile)

Max Activating Token Index: 701

Text #5

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1280. Min Act: -0.0000

Data Index: 648947 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1104. Min Act: -0.0000

Data Index: 1885560 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1034. Min Act: -0.0000

Data Index: 413464 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9878. Min Act: -0.0000

Data Index: 985147 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0370. Min Act: -0.0000

Data Index: 264524 (The Pile)

Max Activating Token Index: 6

Text #10

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0349. Min Act: -0.0000

Data Index: 1830554 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9726. Min Act: -0.0000

Data Index: 1073169 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1476578 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1172061 (The Pile)

Max Activating Token Index: 437

Text #14

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0114. Min Act: -0.0000

Data Index: 1464827 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9734. Min Act: -0.0000

Data Index: 926517 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0815. Min Act: -0.0000

Data Index: 649355 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0057. Min Act: -0.0000

Data Index: 825524 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9820. Min Act: -0.0000

Data Index: 414339 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9909. Min Act: 0.0000

Data Index: 1134342 (The Pile)

Max Activating Token Index: 436