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

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

Neuron 3290 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: 0.0770. Min Range: -0.0770

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1299194 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0717. Min Act: -0.0000

Data Index: 239399 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0692. Min Act: -0.0000

Data Index: 382891 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1003589 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0469. Min Act: 0.0000

Data Index: 349848 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0531. Min Act: -0.0000

Data Index: 1070730 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0466. Min Act: -0.0000

Data Index: 974018 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0504. Min Act: -0.0000

Data Index: 126016 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0456. Min Act: -0.0000

Data Index: 1113522 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0456. Min Act: -0.0000

Data Index: 1342192 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0453. Min Act: -0.0000

Data Index: 1255638 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0462. Min Act: -0.0000

Data Index: 164901 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0446. Min Act: -0.0000

Data Index: 820573 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0458. Min Act: -0.0000

Data Index: 1231249 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0421. Min Act: -0.0000

Data Index: 684206 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1316193 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0456. Min Act: -0.0000

Data Index: 695252 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0391. Min Act: -0.0000

Data Index: 204955 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0439. Min Act: -0.0000

Data Index: 859365 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0401. Min Act: -0.0000

Data Index: 710577 (C4 (Web Text))

Max Activating Token Index: 723