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

Dataset: The Pile

Neuron 2835 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1083283 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.6415. Min Act: -0.0000

Data Index: 361351 (The Pile)

Max Activating Token Index: 794

Text #2

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1559370 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5570. Min Act: -0.0000

Data Index: 619412 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1741070 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1956438 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5129. Min Act: -0.0000

Data Index: 863745 (The Pile)

Max Activating Token Index: 256

Text #7

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5059. Min Act: -0.0000

Data Index: 512319 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.4980. Min Act: -0.0000

Data Index: 478283 (The Pile)

Max Activating Token Index: 927

Text #9

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5743. Min Act: -0.0000

Data Index: 119826 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5514. Min Act: -0.0000

Data Index: 510410 (The Pile)

Max Activating Token Index: 885

Text #11

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5266. Min Act: -0.0000

Data Index: 142513 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1633849 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5006. Min Act: -0.0000

Data Index: 179198 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1888658 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.4877. Min Act: -0.0000

Data Index: 201842 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1271484 (The Pile)

Max Activating Token Index: 779

Text #17

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1592833 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5077. Min Act: -0.0000

Data Index: 5967 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1138215 (The Pile)

Max Activating Token Index: 632