Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3788 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.6435. Min Act: -0.0000

Data Index: 112376 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.4846. Min Act: -0.0000

Data Index: 1047146 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.6105. Min Act: -0.0000

Data Index: 643922 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.3806. Min Act: -0.0000

Data Index: 383346 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.4770. Min Act: 0.0000

Data Index: 805431 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.3053. Min Act: -0.0000

Data Index: 685957 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.1397. Min Act: -0.0000

Data Index: 465855 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.1390. Min Act: 0.0000

Data Index: 1238246 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.1184. Min Act: -0.0000

Data Index: 195960 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.1912. Min Act: -0.0000

Data Index: 309587 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.2471. Min Act: -0.0000

Data Index: 1336908 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.0491. Min Act: -0.0000

Data Index: 519395 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.1743. Min Act: -0.0000

Data Index: 239018 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 2.6435. Min Range: -2.6435

Max Act: 1.9536. Min Act: -0.0000

Data Index: 1266103 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.0090. Min Act: -0.0000

Data Index: 1254288 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 2.6435. Min Range: -2.6435

Max Act: 2.0984. Min Act: -0.0000

Data Index: 760712 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 2.6435. Min Range: -2.6435

Max Act: 1.9845. Min Act: -0.0000

Data Index: 625067 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 2.6435. Min Range: -2.6435

Max Act: 1.9670. Min Act: -0.0000

Data Index: 195121 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 2.6435. Min Range: -2.6435

Max Act: 1.9464. Min Act: -0.0000

Data Index: 666152 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 2.6435. Min Range: -2.6435

Max Act: 1.9429. Min Act: -0.0000

Data Index: 1169635 (C4 (Web Text))

Max Activating Token Index: 421