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

Dataset: The Pile

Neuron 1697 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1147532 (The Pile)

Max Activating Token Index: 414

Text #1

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1833289 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4534. Min Act: -0.0000

Data Index: 579835 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4199. Min Act: -0.0000

Data Index: 255934 (The Pile)

Max Activating Token Index: 8

Text #4

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4204. Min Act: -0.0000

Data Index: 312523 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4355. Min Act: -0.0000

Data Index: 882954 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1289410 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1839924 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1939259 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1675104 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1076698 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1439947 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4274. Min Act: -0.0000

Data Index: 467312 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1845552 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1343561 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3984. Min Act: -0.0000

Data Index: 868416 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4024. Min Act: -0.0001

Data Index: 1727567 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1351589 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3890. Min Act: -0.0000

Data Index: 606846 (The Pile)

Max Activating Token Index: 360

Text #19

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1643772 (The Pile)

Max Activating Token Index: 15