Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 800 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1050675 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0483. Min Act: -0.0002

Data Index: 939907 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0452. Min Act: -0.0002

Data Index: 923009 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0448. Min Act: -0.0002

Data Index: 941790 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0421. Min Act: -0.0002

Data Index: 401085 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1346126 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0393. Min Act: -0.0002

Data Index: 733055 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0383. Min Act: -0.0002

Data Index: 701753 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0382. Min Act: -0.0002

Data Index: 322400 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0374. Min Act: -0.0002

Data Index: 89531 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1302057 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0367. Min Act: -0.0002

Data Index: 680131 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1000071 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0380. Min Act: -0.0002

Data Index: 891 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0366. Min Act: -0.0002

Data Index: 82662 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1169587 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0366. Min Act: -0.0002

Data Index: 699473 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0363. Min Act: -0.0002

Data Index: 119245 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0362. Min Act: -0.0002

Data Index: 361885 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0358. Min Act: -0.0002

Data Index: 552065 (C4 (Web Text))

Max Activating Token Index: 1018