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

Dataset: The Pile

Neuron 4944 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: 0.4829. Min Range: -0.4829

Max Act: 0.4829. Min Act: -0.0000

Data Index: 408447 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1149683 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1278546 (The Pile)

Max Activating Token Index: 398

Text #3

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3869. Min Act: -0.0000

Data Index: 37647 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1156899 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3205. Min Act: -0.0000

Data Index: 234689 (The Pile)

Max Activating Token Index: 650

Text #6

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3418. Min Act: -0.0000

Data Index: 630844 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1999226 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1757376 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3211. Min Act: -0.0000

Data Index: 150254 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1115286 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3253. Min Act: -0.0000

Data Index: 303659 (The Pile)

Max Activating Token Index: 343

Text #12

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1800101 (The Pile)

Max Activating Token Index: 983

Text #13

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1663617 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1683443 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3118. Min Act: -0.0000

Data Index: 540281 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1040832 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3124. Min Act: -0.0000

Data Index: 45302 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3515. Min Act: -0.0000

Data Index: 319575 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1150594 (The Pile)

Max Activating Token Index: 270