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

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

Neuron 339 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0464. Min Act: -0.0005

Data Index: 226328 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0448. Min Act: -0.0005

Data Index: 449728 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0468. Min Act: -0.0005

Data Index: 400506 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0409. Min Act: -0.0005

Data Index: 1092688 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0426. Min Act: -0.0005

Data Index: 1175212 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0429. Min Act: -0.0005

Data Index: 297606 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0423. Min Act: -0.0005

Data Index: 738735 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0419. Min Act: -0.0005

Data Index: 234363 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0429. Min Act: -0.0005

Data Index: 402184 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0417. Min Act: -0.0005

Data Index: 592720 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0402. Min Act: -0.0005

Data Index: 936548 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0384. Min Act: -0.0005

Data Index: 476254 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0409. Min Act: -0.0005

Data Index: 563277 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0402. Min Act: -0.0005

Data Index: 1617704 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0408. Min Act: -0.0005

Data Index: 303693 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0409. Min Act: -0.0005

Data Index: 1262995 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0395. Min Act: -0.0005

Data Index: 1207519 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0395. Min Act: -0.0005

Data Index: 189333 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0390. Min Act: -0.0005

Data Index: 1356916 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0390. Min Act: -0.0005

Data Index: 1225940 (C4 (Web Text))

Max Activating Token Index: 693