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

Dataset: The Pile

Neuron 109 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: 3.9550. Min Range: -3.9550

Max Act: 3.9550. Min Act: -0.0000

Data Index: 1861837 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.9184. Min Act: -0.0000

Data Index: 1171471 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.5479. Min Act: -0.0000

Data Index: 29127 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.3009. Min Act: -0.0000

Data Index: 372749 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.4040. Min Act: -0.0000

Data Index: 241063 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.2550. Min Act: -0.0000

Data Index: 748070 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.2018. Min Act: -0.0000

Data Index: 241415 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.1681. Min Act: -0.0000

Data Index: 485949 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.1597. Min Act: -0.0000

Data Index: 940763 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.4017. Min Act: -0.0000

Data Index: 1385681 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.2378. Min Act: -0.0000

Data Index: 1517072 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.0890. Min Act: -0.0000

Data Index: 731981 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.2166. Min Act: -0.0000

Data Index: 1553786 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.2069. Min Act: -0.0000

Data Index: 825919 (The Pile)

Max Activating Token Index: 50

Text #14

Max Range: 3.9550. Min Range: -3.9550

Max Act: 2.9288. Min Act: -0.0000

Data Index: 941090 (The Pile)

Max Activating Token Index: 915

Text #15

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.4433. Min Act: -0.0000

Data Index: 119128 (The Pile)

Max Activating Token Index: 624

Text #16

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.1130. Min Act: -0.0000

Data Index: 165897 (The Pile)

Max Activating Token Index: 320

Text #17

Max Range: 3.9550. Min Range: -3.9550

Max Act: 2.9937. Min Act: -0.0000

Data Index: 697715 (The Pile)

Max Activating Token Index: 394

Text #18

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.0898. Min Act: -0.0000

Data Index: 601679 (The Pile)

Max Activating Token Index: 795

Text #19

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.1324. Min Act: -0.0000

Data Index: 1276815 (The Pile)

Max Activating Token Index: 903