Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5132 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1870. Min Range: -1.1870

Max Act: 1.1870. Min Act: -0.0000

Data Index: 862895 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7263. Min Act: -0.0000

Data Index: 73197 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7950. Min Act: -0.0000

Data Index: 35816 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1116354 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7203. Min Act: -0.0000

Data Index: 228328 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.8372. Min Act: -0.0000

Data Index: 851317 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7447. Min Act: -0.0000

Data Index: 391875 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7546. Min Act: -0.0000

Data Index: 261014 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7162. Min Act: -0.0000

Data Index: 905076 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7291. Min Act: -0.0000

Data Index: 683985 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1004832 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1163424 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7657. Min Act: -0.0000

Data Index: 973084 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7901. Min Act: -0.0000

Data Index: 372156 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7160. Min Act: -0.0000

Data Index: 74905 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.6558. Min Act: -0.0000

Data Index: 655897 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1482780 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1346642 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.7428. Min Act: -0.0000

Data Index: 391609 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 1.1870. Min Range: -1.1870

Max Act: 0.6832. Min Act: -0.0000

Data Index: 88072 (C4 (Web Text))

Max Activating Token Index: 713