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

Dataset: The Pile

Neuron 3008 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: 0.7550. Min Range: -0.7550

Max Act: 0.7550. Min Act: -0.0000

Data Index: 638629 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1166311 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1273755 (The Pile)

Max Activating Token Index: 549

Text #3

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1268750 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1503009 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1205840 (The Pile)

Max Activating Token Index: 100

Text #6

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1899799 (The Pile)

Max Activating Token Index: 240

Text #7

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5976. Min Act: -0.0000

Data Index: 774267 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1912196 (The Pile)

Max Activating Token Index: 739

Text #9

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1317598 (The Pile)

Max Activating Token Index: 741

Text #10

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1635776 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1700278 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5645. Min Act: -0.0000

Data Index: 925876 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5710. Min Act: -0.0000

Data Index: 949753 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5579. Min Act: -0.0000

Data Index: 100358 (The Pile)

Max Activating Token Index: 674

Text #15

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5210. Min Act: -0.0000

Data Index: 911460 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1715425 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1518752 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1684188 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 0.7550. Min Range: -0.7550

Max Act: 0.5063. Min Act: -0.0000

Data Index: 976620 (The Pile)

Max Activating Token Index: 95