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

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

Neuron 3000 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.2367. Min Act: -0.0000

Data Index: 661157 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.9525. Min Act: -0.0000

Data Index: 169227 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1311. Min Act: -0.0000

Data Index: 533065 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.9755. Min Act: -0.0000

Data Index: 700460 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1009. Min Act: -0.0000

Data Index: 50614 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.0839. Min Act: -0.0000

Data Index: 285364 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.0572. Min Act: -0.0000

Data Index: 1243127 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.9300. Min Act: -0.0000

Data Index: 993589 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.0529. Min Act: -0.0000

Data Index: 587577 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.0210. Min Act: -0.0000

Data Index: 853072 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.9114. Min Act: -0.0000

Data Index: 505954 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.9848. Min Act: -0.0000

Data Index: 1332131 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.9542. Min Act: -0.0000

Data Index: 446285 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.9425. Min Act: -0.0000

Data Index: 938440 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.9447. Min Act: -0.0000

Data Index: 1238852 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.9429. Min Act: -0.0000

Data Index: 421049 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.9296. Min Act: -0.0000

Data Index: 118469 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.0079. Min Act: -0.0000

Data Index: 171833 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.7152. Min Act: -0.0000

Data Index: 919777 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.8901. Min Act: -0.0000

Data Index: 529191 (C4 (Web Text))

Max Activating Token Index: 268