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

Dataset: The Pile

Neuron 1239 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: 0.6890. Min Range: -0.6890

Max Act: 0.6890. Min Act: -0.0000

Data Index: 584015 (The Pile)

Max Activating Token Index: 701

Text #1

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5445. Min Act: -0.0000

Data Index: 785867 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1598818 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4650. Min Act: -0.0000

Data Index: 500527 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1948153 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1771350 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3569. Min Act: -0.0000

Data Index: 916344 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1281970 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3539. Min Act: -0.0000

Data Index: 218684 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3060. Min Act: -0.0000

Data Index: 652587 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1741972 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1016333 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3060. Min Act: -0.0000

Data Index: 771162 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1607112 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3007. Min Act: -0.0000

Data Index: 992579 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3106. Min Act: -0.0000

Data Index: 968831 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.2830. Min Act: -0.0000

Data Index: 554918 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1730435 (The Pile)

Max Activating Token Index: 688

Text #18

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.2789. Min Act: -0.0000

Data Index: 848139 (The Pile)

Max Activating Token Index: 766

Text #19

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1019420 (The Pile)

Max Activating Token Index: 420