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

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

Neuron 1478 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: 0.2964. Min Range: -0.2964

Max Act: 0.2964. Min Act: -0.0000

Data Index: 421916 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2284. Min Act: -0.0000

Data Index: 675059 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1037616 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1446010 (Python Code)

Max Activating Token Index: 190

Text #4

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1392610 (Python Code)

Max Activating Token Index: 749

Text #5

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2148. Min Act: -0.0000

Data Index: 97131 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1532189 (Python Code)

Max Activating Token Index: 335

Text #7

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1542183 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1502080 (Python Code)

Max Activating Token Index: 243

Text #9

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1581658 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1436967 (Python Code)

Max Activating Token Index: 656

Text #11

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1473929 (Python Code)

Max Activating Token Index: 666

Text #12

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1481093 (Python Code)

Max Activating Token Index: 679

Text #13

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1485533 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1716. Min Act: -0.0000

Data Index: 769866 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1824. Min Act: -0.0000

Data Index: 937094 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1489248 (Python Code)

Max Activating Token Index: 798

Text #17

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1511585 (Python Code)

Max Activating Token Index: 153

Text #18

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1327451 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1418796 (Python Code)

Max Activating Token Index: 408