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

Dataset: The Pile

Neuron 3018 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.6632. Min Act: -0.0000

Data Index: 1903940 (The Pile)

Max Activating Token Index: 918

Text #1

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.3771. Min Act: -0.0000

Data Index: 1577743 (The Pile)

Max Activating Token Index: 871

Text #2

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.2139. Min Act: -0.0000

Data Index: 1719926 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.3315. Min Act: -0.0000

Data Index: 1219619 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.1820. Min Act: -0.0000

Data Index: 1669944 (The Pile)

Max Activating Token Index: 850

Text #5

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.2706. Min Act: -0.0000

Data Index: 1819191 (The Pile)

Max Activating Token Index: 410

Text #6

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.4068. Min Act: -0.0000

Data Index: 807257 (The Pile)

Max Activating Token Index: 539

Text #7

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.0899. Min Act: -0.0000

Data Index: 803523 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.3054. Min Act: -0.0000

Data Index: 1459538 (The Pile)

Max Activating Token Index: 313

Text #9

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.1766. Min Act: -0.0000

Data Index: 898145 (The Pile)

Max Activating Token Index: 559

Text #10

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.1981. Min Act: -0.0000

Data Index: 225421 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1573237 (The Pile)

Max Activating Token Index: 653

Text #12

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.1059. Min Act: -0.0000

Data Index: 322554 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.1624. Min Act: -0.0000

Data Index: 1453709 (The Pile)

Max Activating Token Index: 494

Text #14

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.2104. Min Act: -0.0001

Data Index: 1730665 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.2489. Min Act: -0.0000

Data Index: 42093 (The Pile)

Max Activating Token Index: 590

Text #16

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.0464. Min Act: -0.0000

Data Index: 805978 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.2412. Min Act: -0.0000

Data Index: 958346 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.0608. Min Act: -0.0000

Data Index: 810616 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 1.6632. Min Range: -1.6632

Max Act: 1.1220. Min Act: -0.0000

Data Index: 492375 (The Pile)

Max Activating Token Index: 845