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

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

Neuron 1847 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1303900 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2328. Min Act: -0.0000

Data Index: 464508 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2146. Min Act: -0.0000

Data Index: 1319982 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1163852 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1893. Min Act: -0.0000

Data Index: 18774 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1283447 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1970. Min Act: -0.0000

Data Index: 464260 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1057135 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2016. Min Act: -0.0000

Data Index: 668670 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2015. Min Act: -0.0000

Data Index: 151290 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2024. Min Act: -0.0000

Data Index: 956795 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1827. Min Act: -0.0000

Data Index: 204094 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1770 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1826. Min Act: -0.0000

Data Index: 622190 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1616. Min Act: -0.0000

Data Index: 829545 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1955. Min Act: -0.0000

Data Index: 507462 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1854. Min Act: -0.0000

Data Index: 926730 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1844. Min Act: -0.0000

Data Index: 281903 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1247622 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1679. Min Act: -0.0000

Data Index: 739042 (C4 (Web Text))

Max Activating Token Index: 680