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

Dataset: The Pile

Neuron 1855 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: 0.9955. Min Range: -0.9955

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1792749 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.9808. Min Act: -0.0000

Data Index: 609024 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1954336 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1344595 (The Pile)

Max Activating Token Index: 384

Text #4

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8139. Min Act: -0.0000

Data Index: 389540 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1091577 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1446719 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1927871 (The Pile)

Max Activating Token Index: 167

Text #8

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1076809 (The Pile)

Max Activating Token Index: 704

Text #9

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8232. Min Act: -0.0000

Data Index: 332486 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7569. Min Act: -0.0000

Data Index: 646146 (The Pile)

Max Activating Token Index: 844

Text #11

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7991. Min Act: -0.0000

Data Index: 591242 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7951. Min Act: -0.0000

Data Index: 10897 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1864484 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7997. Min Act: -0.0000

Data Index: 868030 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.8020. Min Act: -0.0000

Data Index: 403258 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7335. Min Act: -0.0000

Data Index: 916849 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1957709 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1274230 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1143893 (The Pile)

Max Activating Token Index: 789