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

Dataset: The Pile

Neuron 4041 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: 1.2992. Min Range: -1.2992

Max Act: 1.2393. Min Act: -0.0000

Data Index: 1085408 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.2992. Min Act: -0.0000

Data Index: 666398 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0597. Min Act: -0.0000

Data Index: 1512773 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1506919 (The Pile)

Max Activating Token Index: 723

Text #4

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1614819 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.2216. Min Act: -0.0000

Data Index: 824070 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.2631. Min Act: -0.0000

Data Index: 181340 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1982880 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0821. Min Act: -0.0000

Data Index: 997140 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1288844 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1593057 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1829408 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1367563 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1578983 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1011603 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0222. Min Act: -0.0000

Data Index: 506669 (The Pile)

Max Activating Token Index: 550

Text #16

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.9604. Min Act: -0.0000

Data Index: 172172 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1179278 (The Pile)

Max Activating Token Index: 927

Text #18

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1117662 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.9823. Min Act: -0.0000

Data Index: 411862 (The Pile)

Max Activating Token Index: 62