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

Dataset: The Pile

Neuron 954 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: 0.7426. Min Range: -0.7426

Max Act: 0.7426. Min Act: -0.0000

Data Index: 62981 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1750627 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6792. Min Act: -0.0000

Data Index: 1934632 (The Pile)

Max Activating Token Index: 687

Text #3

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1139734 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.7090. Min Act: -0.0000

Data Index: 203777 (The Pile)

Max Activating Token Index: 620

Text #5

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6904. Min Act: -0.0000

Data Index: 383241 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6863. Min Act: -0.0000

Data Index: 114386 (The Pile)

Max Activating Token Index: 65

Text #7

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1504277 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1175660 (The Pile)

Max Activating Token Index: 27

Text #9

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1106936 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1309123 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1540479 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1011662 (The Pile)

Max Activating Token Index: 267

Text #13

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1414405 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1865183 (The Pile)

Max Activating Token Index: 60

Text #15

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1202943 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6421. Min Act: -0.0000

Data Index: 411085 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1436183 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1343061 (The Pile)

Max Activating Token Index: 15

Text #19

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6047. Min Act: -0.0000

Data Index: 480652 (The Pile)

Max Activating Token Index: 31