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

Dataset: The Pile

Neuron 2613 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: 1.6817. Min Range: -1.6817

Max Act: 1.6817. Min Act: -0.0000

Data Index: 452603 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.3848. Min Act: -0.0000

Data Index: 846623 (The Pile)

Max Activating Token Index: 28

Text #2

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2412. Min Act: -0.0000

Data Index: 840722 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1840113 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1486. Min Act: -0.0000

Data Index: 1733965 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2261. Min Act: -0.0000

Data Index: 918930 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2573. Min Act: -0.0000

Data Index: 1520936 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.3411. Min Act: -0.0000

Data Index: 884664 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2570. Min Act: -0.0000

Data Index: 1941186 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.3755. Min Act: -0.0000

Data Index: 951301 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2325. Min Act: -0.0000

Data Index: 1581558 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2287. Min Act: -0.0000

Data Index: 891700 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1910. Min Act: -0.0000

Data Index: 119954 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2428. Min Act: -0.0000

Data Index: 225512 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2007. Min Act: -0.0000

Data Index: 310250 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1402. Min Act: -0.0000

Data Index: 345764 (The Pile)

Max Activating Token Index: 225

Text #16

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1741. Min Act: -0.0000

Data Index: 1698390 (The Pile)

Max Activating Token Index: 45

Text #17

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.0638. Min Act: -0.0000

Data Index: 112634 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1692424 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1473257 (The Pile)

Max Activating Token Index: 110