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

Dataset: The Pile

Neuron 3879 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: 1.4796. Min Range: -1.4796

Max Act: 1.4796. Min Act: -0.0000

Data Index: 1098633 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1670162 (The Pile)

Max Activating Token Index: 968

Text #2

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.3748. Min Act: -0.0000

Data Index: 1558109 (The Pile)

Max Activating Token Index: 58

Text #3

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.2422. Min Act: -0.0000

Data Index: 1924959 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.2620. Min Act: -0.0000

Data Index: 782214 (The Pile)

Max Activating Token Index: 65

Text #5

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1435. Min Act: -0.0000

Data Index: 946484 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1442. Min Act: -0.0000

Data Index: 1504109 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1651. Min Act: -0.0000

Data Index: 842045 (The Pile)

Max Activating Token Index: 740

Text #8

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.2256. Min Act: -0.0000

Data Index: 1574238 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1162017 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1813. Min Act: -0.0000

Data Index: 438597 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1878226 (The Pile)

Max Activating Token Index: 48

Text #12

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1351533 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1386193 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0304. Min Act: -0.0000

Data Index: 417918 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1569582 (The Pile)

Max Activating Token Index: 24

Text #16

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0914. Min Act: -0.0000

Data Index: 940175 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0720. Min Act: -0.0000

Data Index: 690851 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0284. Min Act: -0.0000

Data Index: 229509 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 1.4796. Min Range: -1.4796

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1645662 (The Pile)

Max Activating Token Index: 722