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

Dataset: The Pile

Neuron 4528 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: 1.8640. Min Range: -1.8640

Max Act: 1.8435. Min Act: -0.0000

Data Index: 377990 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.7119. Min Act: -0.0000

Data Index: 543264 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.8640. Min Act: -0.0000

Data Index: 1650766 (The Pile)

Max Activating Token Index: 577

Text #3

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.7186. Min Act: -0.0000

Data Index: 144935 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.6047. Min Act: -0.0000

Data Index: 1238030 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.5943. Min Act: -0.0000

Data Index: 1317167 (The Pile)

Max Activating Token Index: 312

Text #6

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.4734. Min Act: -0.0000

Data Index: 1118862 (The Pile)

Max Activating Token Index: 203

Text #7

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.1274. Min Act: -0.0000

Data Index: 61659 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.3912. Min Act: -0.0000

Data Index: 902230 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.4691. Min Act: -0.0000

Data Index: 1979844 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.3022. Min Act: -0.0000

Data Index: 243107 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.3744. Min Act: -0.0000

Data Index: 939624 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.4203. Min Act: -0.0000

Data Index: 1624691 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1173349 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.2761. Min Act: -0.0000

Data Index: 818862 (The Pile)

Max Activating Token Index: 400

Text #15

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.3340. Min Act: -0.0000

Data Index: 842816 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.2566. Min Act: -0.0000

Data Index: 1153894 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.2542. Min Act: -0.0000

Data Index: 1797167 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.2569. Min Act: -0.0000

Data Index: 1688921 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.3053. Min Act: -0.0000

Data Index: 1559978 (The Pile)

Max Activating Token Index: 327