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

Dataset: The Pile

Neuron 4253 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0999. Min Range: -1.0999

Max Act: 1.0999. Min Act: -0.0000

Data Index: 774929 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.9611. Min Act: -0.0000

Data Index: 718930 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.9306. Min Act: -0.0000

Data Index: 24642 (The Pile)

Max Activating Token Index: 678

Text #3

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1528776 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.9010. Min Act: -0.0000

Data Index: 227718 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8935. Min Act: -0.0000

Data Index: 924576 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.9233. Min Act: -0.0000

Data Index: 70923 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1966253 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1020669 (The Pile)

Max Activating Token Index: 259

Text #9

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1677282 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8674. Min Act: -0.0000

Data Index: 484866 (The Pile)

Max Activating Token Index: 659

Text #11

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8474. Min Act: -0.0000

Data Index: 286385 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8444. Min Act: -0.0000

Data Index: 145929 (The Pile)

Max Activating Token Index: 442

Text #13

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8398. Min Act: -0.0000

Data Index: 420063 (The Pile)

Max Activating Token Index: 7

Text #14

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1330399 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1555465 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6718. Min Act: -0.0000

Data Index: 600935 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.7732. Min Act: -0.0000

Data Index: 696864 (The Pile)

Max Activating Token Index: 548

Text #18

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.7106. Min Act: -0.0000

Data Index: 586775 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1166077 (The Pile)

Max Activating Token Index: 203