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

Dataset: The Pile

Neuron 993 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: 0.9033. Min Range: -0.9033

Max Act: 0.9033. Min Act: -0.0000

Data Index: 658183 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1074869 (The Pile)

Max Activating Token Index: 243

Text #2

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7530. Min Act: -0.0000

Data Index: 521185 (The Pile)

Max Activating Token Index: 937

Text #3

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1719370 (The Pile)

Max Activating Token Index: 754

Text #4

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1421614 (The Pile)

Max Activating Token Index: 275

Text #5

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6893. Min Act: -0.0000

Data Index: 752090 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1613523 (The Pile)

Max Activating Token Index: 63

Text #7

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6108. Min Act: -0.0000

Data Index: 115837 (The Pile)

Max Activating Token Index: 991

Text #8

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1495421 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6662. Min Act: -0.0000

Data Index: 320305 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1332806 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1181301 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1283283 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6633. Min Act: -0.0000

Data Index: 237068 (The Pile)

Max Activating Token Index: 645

Text #14

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1427147 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1135942 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6052. Min Act: -0.0000

Data Index: 879649 (The Pile)

Max Activating Token Index: 355

Text #17

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1039650 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6645. Min Act: -0.0000

Data Index: 315716 (The Pile)

Max Activating Token Index: 833

Text #19

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1670273 (The Pile)

Max Activating Token Index: 570