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

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

Neuron 3146 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.3590. Min Act: -0.0000

Data Index: 620723 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.3126. Min Act: -0.0000

Data Index: 864209 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.3607. Min Act: -0.0000

Data Index: 672968 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.2212. Min Act: -0.0000

Data Index: 885677 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1209893 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.2557. Min Act: -0.0000

Data Index: 398334 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.1137. Min Act: -0.0000

Data Index: 769965 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1085299 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.1581. Min Act: -0.0000

Data Index: 761883 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.1372. Min Act: -0.0000

Data Index: 778253 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.1965. Min Act: -0.0000

Data Index: 468851 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.1240. Min Act: -0.0000

Data Index: 259159 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.0467. Min Act: -0.0000

Data Index: 1347497 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.1032. Min Act: -0.0000

Data Index: 407080 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.0627. Min Act: -0.0000

Data Index: 734851 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.0687. Min Act: -0.0000

Data Index: 855940 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.0662. Min Act: -0.0000

Data Index: 158712 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.0251. Min Act: -0.0000

Data Index: 69113 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.9665. Min Act: -0.0000

Data Index: 338838 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.9294. Min Act: -0.0000

Data Index: 955154 (C4 (Web Text))

Max Activating Token Index: 531