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

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

Neuron 3548 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.3212. Min Act: -0.0001

Data Index: 1035688 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2956. Min Act: -0.0001

Data Index: 1225171 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2535. Min Act: -0.0001

Data Index: 1101798 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2223. Min Act: -0.0001

Data Index: 944369 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1343106 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2001. Min Act: -0.0001

Data Index: 202329 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2028. Min Act: -0.0001

Data Index: 609560 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2040. Min Act: -0.0001

Data Index: 749612 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1926. Min Act: -0.0001

Data Index: 1272436 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1863. Min Act: -0.0001

Data Index: 592433 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1916. Min Act: -0.0001

Data Index: 480614 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1968. Min Act: -0.0001

Data Index: 766444 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1757. Min Act: -0.0001

Data Index: 362780 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1948. Min Act: -0.0001

Data Index: 1231043 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1823. Min Act: -0.0001

Data Index: 1357806 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1826. Min Act: -0.0001

Data Index: 424583 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1817. Min Act: -0.0001

Data Index: 1325800 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1852. Min Act: -0.0001

Data Index: 37681 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1609. Min Act: -0.0001

Data Index: 174333 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1808. Min Act: -0.0001

Data Index: 829693 (C4 (Web Text))

Max Activating Token Index: 441