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

Dataset: The Pile

Neuron 3808 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.7164. Min Act: -0.0000

Data Index: 15619 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1481046 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5409. Min Act: 0.0000

Data Index: 933010 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1277026 (The Pile)

Max Activating Token Index: 87

Text #4

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4993. Min Act: -0.0000

Data Index: 441783 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4956. Min Act: -0.0000

Data Index: 995428 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4722. Min Act: -0.0000

Data Index: 893741 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1829420 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1771153 (The Pile)

Max Activating Token Index: 15

Text #9

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4470. Min Act: -0.0000

Data Index: 28419 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1316731 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4015. Min Act: -0.0000

Data Index: 457411 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.3946. Min Act: -0.0000

Data Index: 811459 (The Pile)

Max Activating Token Index: 13

Text #13

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.3946. Min Act: -0.0000

Data Index: 26494 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1940592 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1338415 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.3654. Min Act: -0.0000

Data Index: 599190 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1027013 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.3526. Min Act: -0.0000

Data Index: 123847 (The Pile)

Max Activating Token Index: 48

Text #19

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1675691 (The Pile)

Max Activating Token Index: 47