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

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

Neuron 739 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: 0.3816. Min Range: -0.3816

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1620976 (Python Code)

Max Activating Token Index: 755

Text #1

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.3816. Min Act: -0.0000

Data Index: 310658 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1478609 (Python Code)

Max Activating Token Index: 825

Text #3

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1638629 (Python Code)

Max Activating Token Index: 432

Text #4

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2268. Min Act: -0.0000

Data Index: 205065 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1430782 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2375. Min Act: -0.0000

Data Index: 345986 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1462180 (Python Code)

Max Activating Token Index: 476

Text #8

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2294. Min Act: -0.0000

Data Index: 702910 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1272638 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1363596 (Python Code)

Max Activating Token Index: 389

Text #11

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2601. Min Act: -0.0000

Data Index: 869666 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2076. Min Act: -0.0000

Data Index: 339183 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1647419 (Python Code)

Max Activating Token Index: 212

Text #14

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2160. Min Act: -0.0000

Data Index: 833785 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.1910. Min Act: -0.0000

Data Index: 629553 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.1957. Min Act: -0.0000

Data Index: 694119 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1442183 (Python Code)

Max Activating Token Index: 562

Text #18

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.1883. Min Act: -0.0000

Data Index: 421488 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.3816. Min Range: -0.3816

Max Act: 0.1891. Min Act: -0.0000

Data Index: 738655 (C4 (Web Text))

Max Activating Token Index: 759