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

Dataset: The Pile

Neuron 1826 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7106. Min Range: -5.7106

Max Act: 5.7106. Min Act: -0.0000

Data Index: 539628 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 5.7106. Min Range: -5.7106

Max Act: 5.4918. Min Act: -0.0000

Data Index: 878158 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 5.7106. Min Range: -5.7106

Max Act: 5.0225. Min Act: -0.0000

Data Index: 1441877 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 5.7106. Min Range: -5.7106

Max Act: 5.3621. Min Act: -0.0000

Data Index: 1328267 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 5.7106. Min Range: -5.7106

Max Act: 5.3075. Min Act: -0.0000

Data Index: 1169622 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.9640. Min Act: -0.0000

Data Index: 203492 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.8743. Min Act: -0.0000

Data Index: 712135 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.7801. Min Act: -0.0000

Data Index: 764008 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 5.7106. Min Range: -5.7106

Max Act: 5.1209. Min Act: -0.0000

Data Index: 1829644 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 5.7106. Min Range: -5.7106

Max Act: 5.0333. Min Act: -0.0000

Data Index: 149510 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.8292. Min Act: -0.0000

Data Index: 1776078 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.8285. Min Act: -0.0000

Data Index: 278767 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.7840. Min Act: -0.0000

Data Index: 1873016 (The Pile)

Max Activating Token Index: 631

Text #13

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.7785. Min Act: -0.0000

Data Index: 908001 (The Pile)

Max Activating Token Index: 592

Text #14

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.7425. Min Act: -0.0000

Data Index: 928832 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.7381. Min Act: -0.0000

Data Index: 1171832 (The Pile)

Max Activating Token Index: 472

Text #16

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.5144. Min Act: -0.0000

Data Index: 131411 (The Pile)

Max Activating Token Index: 22

Text #17

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.3545. Min Act: -0.0000

Data Index: 1578844 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.7258. Min Act: -0.0000

Data Index: 1743954 (The Pile)

Max Activating Token Index: 406

Text #19

Max Range: 5.7106. Min Range: -5.7106

Max Act: 4.8602. Min Act: -0.0000

Data Index: 1250705 (The Pile)

Max Activating Token Index: 169