Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2012 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0003

Data Index: 530261 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0560. Min Act: -0.0003

Data Index: 747079 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0555. Min Act: -0.0003

Data Index: 921649 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0549. Min Act: -0.0002

Data Index: 194168 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1216019 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0530. Min Act: -0.0002

Data Index: 880256 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0532. Min Act: -0.0003

Data Index: 984585 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0535. Min Act: -0.0003

Data Index: 663538 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1312167 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0520. Min Act: -0.0004

Data Index: 215227 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0514. Min Act: -0.0003

Data Index: 682819 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0519. Min Act: -0.0001

Data Index: 697904 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0536. Min Act: -0.0003

Data Index: 940771 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0517. Min Act: -0.0003

Data Index: 31859 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0521. Min Act: -0.0004

Data Index: 455668 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0506. Min Act: -0.0003

Data Index: 119191 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1278040 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1103093 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0512. Min Act: -0.0003

Data Index: 339499 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0513. Min Act: -0.0002

Data Index: 370237 (C4 (Web Text))

Max Activating Token Index: 629