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

Dataset: The Pile

Neuron 2127 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1731. Min Range: -7.1731

Max Act: 7.1731. Min Act: -0.0000

Data Index: 1592482 (The Pile)

Max Activating Token Index: 239

Text #1

Max Range: 7.1731. Min Range: -7.1731

Max Act: 6.6123. Min Act: -0.0000

Data Index: 725508 (The Pile)

Max Activating Token Index: 81

Text #2

Max Range: 7.1731. Min Range: -7.1731

Max Act: 6.3342. Min Act: -0.0000

Data Index: 290196 (The Pile)

Max Activating Token Index: 64

Text #3

Max Range: 7.1731. Min Range: -7.1731

Max Act: 5.8404. Min Act: -0.0000

Data Index: 1993527 (The Pile)

Max Activating Token Index: 732

Text #4

Max Range: 7.1731. Min Range: -7.1731

Max Act: 5.1532. Min Act: -0.0000

Data Index: 1190987 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 7.1731. Min Range: -7.1731

Max Act: 5.1031. Min Act: -0.0000

Data Index: 1295316 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 7.1731. Min Range: -7.1731

Max Act: 4.9240. Min Act: -0.0000

Data Index: 1825873 (The Pile)

Max Activating Token Index: 63

Text #7

Max Range: 7.1731. Min Range: -7.1731

Max Act: 5.0721. Min Act: -0.0000

Data Index: 333254 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 7.1731. Min Range: -7.1731

Max Act: 5.3523. Min Act: -0.0000

Data Index: 1139653 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 7.1731. Min Range: -7.1731

Max Act: 5.2955. Min Act: -0.0000

Data Index: 1165758 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 7.1731. Min Range: -7.1731

Max Act: 4.7002. Min Act: -0.0000

Data Index: 1250456 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 7.1731. Min Range: -7.1731

Max Act: 4.3545. Min Act: -0.0000

Data Index: 1061155 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 7.1731. Min Range: -7.1731

Max Act: 4.4748. Min Act: -0.0000

Data Index: 100790 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 7.1731. Min Range: -7.1731

Max Act: 4.4508. Min Act: -0.0000

Data Index: 1382528 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 7.1731. Min Range: -7.1731

Max Act: 4.0614. Min Act: -0.0000

Data Index: 1504759 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 7.1731. Min Range: -7.1731

Max Act: 4.2180. Min Act: -0.0000

Data Index: 673530 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 7.1731. Min Range: -7.1731

Max Act: 3.6495. Min Act: -0.0000

Data Index: 498382 (The Pile)

Max Activating Token Index: 832

Text #17

Max Range: 7.1731. Min Range: -7.1731

Max Act: 4.3806. Min Act: -0.0000

Data Index: 1799610 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 7.1731. Min Range: -7.1731

Max Act: 3.8924. Min Act: -0.0000

Data Index: 1094186 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 7.1731. Min Range: -7.1731

Max Act: 3.9248. Min Act: -0.0000

Data Index: 1254726 (The Pile)

Max Activating Token Index: 310