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

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

Neuron 5079 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0504. Min Act: -0.0002

Data Index: 147135 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0479. Min Act: -0.0002

Data Index: 307611 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0453. Min Act: -0.0002

Data Index: 893366 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0446. Min Act: -0.0002

Data Index: 516127 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0423. Min Act: -0.0002

Data Index: 319861 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0404. Min Act: -0.0002

Data Index: 383996 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1275697 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0401. Min Act: -0.0002

Data Index: 20632 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1055443 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1380090 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0391. Min Act: -0.0002

Data Index: 450932 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0366. Min Act: -0.0002

Data Index: 453272 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1248666 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0375. Min Act: -0.0002

Data Index: 229391 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0385. Min Act: -0.0002

Data Index: 159272 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1425700 (Python Code)

Max Activating Token Index: 379

Text #16

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0361. Min Act: -0.0002

Data Index: 166548 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0356. Min Act: -0.0002

Data Index: 772463 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0340. Min Act: -0.0002

Data Index: 756585 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0339. Min Act: -0.0002

Data Index: 411182 (C4 (Web Text))

Max Activating Token Index: 301