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

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

Neuron 529 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.5863. Min Act: -0.0002

Data Index: 427003 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.3673. Min Act: -0.0002

Data Index: 134455 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.1766. Min Act: -0.0002

Data Index: 830707 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.1736. Min Act: -0.0002

Data Index: 1237889 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.1380. Min Act: -0.0002

Data Index: 1184876 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.5863. Min Range: -3.5863

Max Act: 2.9728. Min Act: -0.0002

Data Index: 570 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.1043. Min Act: -0.0002

Data Index: 634055 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.2298. Min Act: -0.0002

Data Index: 1317937 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.0877. Min Act: -0.0002

Data Index: 227006 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 3.5863. Min Range: -3.5863

Max Act: 2.9509. Min Act: -0.0002

Data Index: 624494 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.0397. Min Act: -0.0002

Data Index: 941588 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 3.5863. Min Range: -3.5863

Max Act: 2.9003. Min Act: -0.0002

Data Index: 1341305 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 3.5863. Min Range: -3.5863

Max Act: 2.9945. Min Act: -0.0002

Data Index: 296389 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 3.5863. Min Range: -3.5863

Max Act: 3.0070. Min Act: -0.0002

Data Index: 745324 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 3.5863. Min Range: -3.5863

Max Act: 2.9675. Min Act: -0.0002

Data Index: 748608 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 3.5863. Min Range: -3.5863

Max Act: 2.9882. Min Act: -0.0002

Data Index: 1224536 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 3.5863. Min Range: -3.5863

Max Act: 2.9718. Min Act: -0.0002

Data Index: 1269298 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 3.5863. Min Range: -3.5863

Max Act: 2.8476. Min Act: -0.0002

Data Index: 438453 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 3.5863. Min Range: -3.5863

Max Act: 2.9966. Min Act: -0.0002

Data Index: 209276 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 3.5863. Min Range: -3.5863

Max Act: 2.9642. Min Act: -0.0002

Data Index: 366405 (C4 (Web Text))

Max Activating Token Index: 799