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

Dataset: The Pile

Neuron 725 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: 0.9684. Min Range: -0.9684

Max Act: 0.8906. Min Act: -0.0000

Data Index: 438932 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.9684. Min Act: -0.0000

Data Index: 1726775 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1128773 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.9636. Min Act: -0.0000

Data Index: 812451 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1409904 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8898. Min Act: -0.0000

Data Index: 319745 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.9139. Min Act: -0.0000

Data Index: 318765 (The Pile)

Max Activating Token Index: 84

Text #7

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.9037. Min Act: -0.0000

Data Index: 349735 (The Pile)

Max Activating Token Index: 212

Text #8

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8363. Min Act: -0.0000

Data Index: 237849 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1399475 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1133838 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8698. Min Act: -0.0000

Data Index: 150673 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8185. Min Act: -0.0000

Data Index: 201644 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8913. Min Act: -0.0000

Data Index: 161842 (The Pile)

Max Activating Token Index: 533

Text #14

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1337173 (The Pile)

Max Activating Token Index: 11

Text #15

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1267916 (The Pile)

Max Activating Token Index: 366

Text #16

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8389. Min Act: -0.0000

Data Index: 478450 (The Pile)

Max Activating Token Index: 434

Text #17

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1167117 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1053524 (The Pile)

Max Activating Token Index: 1013

Text #19

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7473. Min Act: -0.0000

Data Index: 195231 (The Pile)

Max Activating Token Index: 785