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

Dataset: The Pile

Neuron 1520 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.2711. Min Act: -0.0000

Data Index: 1069088 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.0439. Min Act: -0.0000

Data Index: 918605 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.9895. Min Act: -0.0000

Data Index: 605724 (The Pile)

Max Activating Token Index: 383

Text #3

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1298753 (The Pile)

Max Activating Token Index: 60

Text #4

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.9092. Min Act: -0.0000

Data Index: 532450 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1142218 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.8241. Min Act: -0.0000

Data Index: 305517 (The Pile)

Max Activating Token Index: 304

Text #7

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1856137 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1985405 (The Pile)

Max Activating Token Index: 751

Text #9

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.7274. Min Act: -0.0000

Data Index: 547389 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.8501. Min Act: -0.0000

Data Index: 1862348 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.7443. Min Act: -0.0000

Data Index: 983187 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1979422 (The Pile)

Max Activating Token Index: 439

Text #13

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.7165. Min Act: -0.0000

Data Index: 576039 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1766988 (The Pile)

Max Activating Token Index: 536

Text #15

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1029688 (The Pile)

Max Activating Token Index: 642

Text #16

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1106999 (The Pile)

Max Activating Token Index: 737

Text #17

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.7769. Min Act: -0.0000

Data Index: 558335 (The Pile)

Max Activating Token Index: 471

Text #18

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.7326. Min Act: -0.0000

Data Index: 982067 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 1.2711. Min Range: -1.2711

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1676472 (The Pile)

Max Activating Token Index: 687