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

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

Neuron 1893 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: 1.5539. Min Range: -1.5539

Max Act: 1.5539. Min Act: -0.0000

Data Index: 1262916 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.4583. Min Act: -0.0000

Data Index: 1214319 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6913. Min Act: -0.0000

Data Index: 354181 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.7442. Min Act: -0.0000

Data Index: 678446 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.8399. Min Act: -0.0000

Data Index: 19163 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6987. Min Act: -0.0000

Data Index: 186123 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.7089. Min Act: -0.0000

Data Index: 226902 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6660. Min Act: -0.0000

Data Index: 240876 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6740. Min Act: -0.0000

Data Index: 313694 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6519. Min Act: -0.0000

Data Index: 323272 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1235304 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.7312. Min Act: -0.0000

Data Index: 434670 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6682. Min Act: -0.0000

Data Index: 862998 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6427. Min Act: -0.0000

Data Index: 363735 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1063137 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1581085 (Python Code)

Max Activating Token Index: 907

Text #16

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6598. Min Act: -0.0000

Data Index: 272348 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6560. Min Act: -0.0000

Data Index: 17807 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6989. Min Act: -0.0000

Data Index: 298653 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1232068 (C4 (Web Text))

Max Activating Token Index: 685