Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1585 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1620275 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5574. Min Act: -0.0000

Data Index: 581808 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1758003 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5221. Min Act: -0.0000

Data Index: 545783 (The Pile)

Max Activating Token Index: 738

Text #4

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4840. Min Act: 0.0000

Data Index: 877033 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1944495 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1367568 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1742012 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1453418 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4570. Min Act: -0.0000

Data Index: 431221 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1313752 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4065. Min Act: 0.0000

Data Index: 1968742 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1429682 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4259. Min Act: -0.0000

Data Index: 173394 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3821. Min Act: 0.0000

Data Index: 916206 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1537723 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4332. Min Act: 0.0000

Data Index: 51825 (The Pile)

Max Activating Token Index: 158

Text #17

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3978. Min Act: -0.0000

Data Index: 865871 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3912. Min Act: -0.0000

Data Index: 992297 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3790. Min Act: -0.0000

Data Index: 583057 (The Pile)

Max Activating Token Index: 504