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

Dataset: The Pile

Neuron 1069 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: 1.0824. Min Range: -1.0824

Max Act: 1.0824. Min Act: -0.0000

Data Index: 733806 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0494. Min Act: -0.0000

Data Index: 1768895 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0022. Min Act: -0.0000

Data Index: 213058 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9993. Min Act: -0.0000

Data Index: 670323 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1341184 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9364. Min Act: -0.0000

Data Index: 258698 (The Pile)

Max Activating Token Index: 802

Text #6

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1921825 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1735070 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9133. Min Act: -0.0000

Data Index: 737766 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1214420 (The Pile)

Max Activating Token Index: 597

Text #10

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8484. Min Act: -0.0000

Data Index: 185686 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1303549 (The Pile)

Max Activating Token Index: 80

Text #12

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8799. Min Act: -0.0000

Data Index: 278669 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8968. Min Act: -0.0000

Data Index: 962004 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1956420 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1137959 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8147. Min Act: -0.0000

Data Index: 285806 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8701. Min Act: -0.0000

Data Index: 189036 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8144. Min Act: -0.0000

Data Index: 23476 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1653635 (The Pile)

Max Activating Token Index: 960