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

Dataset: The Pile

Neuron 22 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: 0.6825. Min Range: -0.6825

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1119480 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6228. Min Act: -0.0000

Data Index: 864640 (The Pile)

Max Activating Token Index: 267

Text #2

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1359504 (The Pile)

Max Activating Token Index: 23

Text #3

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6283. Min Act: -0.0000

Data Index: 74532 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1459670 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5990. Min Act: -0.0000

Data Index: 976892 (The Pile)

Max Activating Token Index: 229

Text #6

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5722. Min Act: -0.0000

Data Index: 446190 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5929. Min Act: -0.0000

Data Index: 494533 (The Pile)

Max Activating Token Index: 334

Text #8

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5929. Min Act: -0.0000

Data Index: 310389 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5930. Min Act: -0.0000

Data Index: 185481 (The Pile)

Max Activating Token Index: 159

Text #10

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1543248 (The Pile)

Max Activating Token Index: 17

Text #11

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5444. Min Act: -0.0000

Data Index: 692192 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1457563 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1875609 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5272. Min Act: -0.0000

Data Index: 254671 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1887846 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1962571 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1274764 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1687471 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5327. Min Act: -0.0000

Data Index: 3884 (The Pile)

Max Activating Token Index: 139