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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1548 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.9715. Min Act: -0.0000

Data Index: 1263939 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 2.0103. Min Range: -2.0103

Max Act: 2.0103. Min Act: -0.0000

Data Index: 66091 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.9058. Min Act: -0.0000

Data Index: 118496 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.8612. Min Act: -0.0000

Data Index: 94521 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.7291. Min Act: -0.0000

Data Index: 1202797 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.7994. Min Act: -0.0000

Data Index: 64868 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.7542. Min Act: -0.0000

Data Index: 707340 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.7317. Min Act: -0.0000

Data Index: 703121 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.7214. Min Act: -0.0001

Data Index: 388419 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.8008. Min Act: -0.0000

Data Index: 133372 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.6977. Min Act: -0.0000

Data Index: 323937 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.6604. Min Act: -0.0000

Data Index: 468241 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.4919. Min Act: -0.0000

Data Index: 265421 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.6509. Min Act: -0.0000

Data Index: 760829 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.6189. Min Act: -0.0000

Data Index: 1352966 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.5086. Min Act: -0.0000

Data Index: 930764 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.5999. Min Act: -0.0000

Data Index: 858811 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.5889. Min Act: -0.0000

Data Index: 763370 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.5895. Min Act: -0.0000

Data Index: 400864 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.5040. Min Act: -0.0000

Data Index: 1199356 (C4 (Web Text))

Max Activating Token Index: 411