Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 107 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0655. Min Act: -0.0001

Data Index: 824834 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0561. Min Act: -0.0001

Data Index: 690877 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0503. Min Act: -0.0001

Data Index: 438322 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0521. Min Act: -0.0001

Data Index: 961150 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0526. Min Act: -0.0001

Data Index: 716389 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1351612 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0504. Min Act: -0.0001

Data Index: 66557 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0509. Min Act: -0.0001

Data Index: 827864 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1618588 (Python Code)

Max Activating Token Index: 133

Text #9

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0538. Min Act: -0.0001

Data Index: 963265 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0473. Min Act: -0.0001

Data Index: 1616936 (Python Code)

Max Activating Token Index: 666

Text #11

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0470. Min Act: -0.0001

Data Index: 880529 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0464. Min Act: -0.0001

Data Index: 653657 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0450. Min Act: -0.0001

Data Index: 84282 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0439. Min Act: -0.0001

Data Index: 820585 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0455. Min Act: -0.0001

Data Index: 990777 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0472. Min Act: -0.0001

Data Index: 811243 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1585703 (Python Code)

Max Activating Token Index: 616

Text #18

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0453. Min Act: -0.0001

Data Index: 244689 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0452. Min Act: -0.0001

Data Index: 897388 (C4 (Web Text))

Max Activating Token Index: 723