Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2796 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1847. Min Act: -0.0004

Data Index: 345039 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1598. Min Act: -0.0004

Data Index: 64410 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1513. Min Act: -0.0004

Data Index: 402021 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1733. Min Act: -0.0004

Data Index: 432733 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1716. Min Act: -0.0004

Data Index: 829706 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1462. Min Act: -0.0004

Data Index: 1056059 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1752. Min Act: -0.0004

Data Index: 727146 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1571. Min Act: -0.0004

Data Index: 1160166 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1463. Min Act: -0.0004

Data Index: 647433 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1458. Min Act: -0.0004

Data Index: 964739 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1623. Min Act: -0.0004

Data Index: 981840 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1393. Min Act: -0.0004

Data Index: 1292231 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1540. Min Act: -0.0004

Data Index: 885384 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1434. Min Act: -0.0004

Data Index: 385101 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1479. Min Act: -0.0004

Data Index: 1095357 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1527. Min Act: -0.0004

Data Index: 1325312 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1530. Min Act: -0.0004

Data Index: 232705 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1519. Min Act: -0.0004

Data Index: 843742 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1523. Min Act: -0.0004

Data Index: 1052895 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1343. Min Act: -0.0004

Data Index: 1266150 (C4 (Web Text))

Max Activating Token Index: 639