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

Dataset: The Pile

Neuron 2674 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: 0.9610. Min Range: -0.9610

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1748372 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1192657 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1387533 (The Pile)

Max Activating Token Index: 113

Text #3

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6548. Min Act: -0.0000

Data Index: 768250 (The Pile)

Max Activating Token Index: 904

Text #4

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1907366 (The Pile)

Max Activating Token Index: 231

Text #5

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6845. Min Act: -0.0000

Data Index: 539900 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7009. Min Act: -0.0000

Data Index: 780460 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6996. Min Act: -0.0000

Data Index: 796834 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1950933 (The Pile)

Max Activating Token Index: 69

Text #9

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1581289 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6832. Min Act: -0.0000

Data Index: 825758 (The Pile)

Max Activating Token Index: 909

Text #11

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1218996 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6543. Min Act: -0.0000

Data Index: 491248 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1523170 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6734. Min Act: -0.0000

Data Index: 917492 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1759105 (The Pile)

Max Activating Token Index: 69

Text #16

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6096. Min Act: -0.0000

Data Index: 341841 (The Pile)

Max Activating Token Index: 539

Text #17

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1811480 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.6324. Min Act: -0.0000

Data Index: 876470 (The Pile)

Max Activating Token Index: 972

Text #19

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.5909. Min Act: -0.0000

Data Index: 875812 (The Pile)

Max Activating Token Index: 248