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

Dataset: The Pile

Neuron 1774 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: 5.8368. Min Range: -5.8368

Max Act: 5.6691. Min Act: -0.0000

Data Index: 1010720 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 5.8368. Min Range: -5.8368

Max Act: 5.8368. Min Act: -0.0000

Data Index: 1224719 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 5.8368. Min Range: -5.8368

Max Act: 5.4899. Min Act: -0.0000

Data Index: 752845 (The Pile)

Max Activating Token Index: 585

Text #3

Max Range: 5.8368. Min Range: -5.8368

Max Act: 5.1943. Min Act: -0.0000

Data Index: 1256653 (The Pile)

Max Activating Token Index: 661

Text #4

Max Range: 5.8368. Min Range: -5.8368

Max Act: 5.4644. Min Act: -0.0000

Data Index: 131619 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 5.8368. Min Range: -5.8368

Max Act: 5.2818. Min Act: -0.0000

Data Index: 1196468 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 5.8368. Min Range: -5.8368

Max Act: 5.3042. Min Act: -0.0000

Data Index: 859387 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 5.8368. Min Range: -5.8368

Max Act: 5.2427. Min Act: -0.0000

Data Index: 681895 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 5.8368. Min Range: -5.8368

Max Act: 4.9695. Min Act: -0.0000

Data Index: 1610638 (The Pile)

Max Activating Token Index: 533

Text #9

Max Range: 5.8368. Min Range: -5.8368

Max Act: 5.4313. Min Act: -0.0000

Data Index: 1018186 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 5.8368. Min Range: -5.8368

Max Act: 5.1804. Min Act: -0.0000

Data Index: 1001729 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 5.8368. Min Range: -5.8368

Max Act: 5.1524. Min Act: -0.0000

Data Index: 1786428 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 5.8368. Min Range: -5.8368

Max Act: 4.7838. Min Act: -0.0000

Data Index: 787109 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 5.8368. Min Range: -5.8368

Max Act: 4.8361. Min Act: -0.0000

Data Index: 146840 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 5.8368. Min Range: -5.8368

Max Act: 4.7705. Min Act: -0.0000

Data Index: 1964632 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 5.8368. Min Range: -5.8368

Max Act: 4.5194. Min Act: -0.0000

Data Index: 542047 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 5.8368. Min Range: -5.8368

Max Act: 4.6208. Min Act: -0.0000

Data Index: 741898 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 5.8368. Min Range: -5.8368

Max Act: 4.3137. Min Act: -0.0000

Data Index: 1658491 (The Pile)

Max Activating Token Index: 978

Text #18

Max Range: 5.8368. Min Range: -5.8368

Max Act: 3.8091. Min Act: -0.0000

Data Index: 1909299 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 5.8368. Min Range: -5.8368

Max Act: 4.3393. Min Act: -0.0000

Data Index: 1630022 (The Pile)

Max Activating Token Index: 435