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

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

Neuron 94 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: 0.0537. Min Range: -0.0537

Max Act: 0.0537. Min Act: -0.0002

Data Index: 787141 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1208538 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1215876 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0463. Min Act: -0.0001

Data Index: 302784 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0480. Min Act: -0.0001

Data Index: 103781 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0453. Min Act: -0.0002

Data Index: 473468 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0438. Min Act: -0.0001

Data Index: 107616 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0448. Min Act: -0.0002

Data Index: 968311 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1249566 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1065579 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1150572 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0432. Min Act: -0.0001

Data Index: 969889 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1267227 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0406. Min Act: -0.0001

Data Index: 439880 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1121812 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0439. Min Act: -0.0001

Data Index: 519760 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0436. Min Act: -0.0002

Data Index: 377341 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1132568 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0417. Min Act: -0.0002

Data Index: 825115 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0423. Min Act: -0.0002

Data Index: 783008 (C4 (Web Text))

Max Activating Token Index: 605