Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2776 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.7009. Min Act: -0.0001

Data Index: 109433 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.5043. Min Act: -0.0001

Data Index: 844492 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.3878. Min Act: -0.0001

Data Index: 15791 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.4654. Min Act: -0.0002

Data Index: 670270 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.3100. Min Act: -0.0001

Data Index: 599635 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.3553. Min Act: -0.0002

Data Index: 693377 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.2928. Min Act: -0.0002

Data Index: 664314 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.2824. Min Act: -0.0001

Data Index: 673332 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.2348. Min Act: -0.0001

Data Index: 831825 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.1890. Min Act: -0.0002

Data Index: 1313956 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.3271. Min Act: -0.0001

Data Index: 917002 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.2115. Min Act: -0.0001

Data Index: 698599 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.1947. Min Act: -0.0001

Data Index: 876655 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.2423. Min Act: -0.0001

Data Index: 505362 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.1748. Min Act: -0.0001

Data Index: 511454 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.2022. Min Act: -0.0001

Data Index: 1057306 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.2715. Min Act: -0.0002

Data Index: 938927 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.2035. Min Act: -0.0002

Data Index: 729220 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.2375. Min Act: -0.0001

Data Index: 921600 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 1.7009. Min Range: -1.7009

Max Act: 1.2508. Min Act: -0.0001

Data Index: 948642 (C4 (Web Text))

Max Activating Token Index: 105