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

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

Neuron 378 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: 0.1781. Min Range: -0.1781

Max Act: 0.1781. Min Act: -0.0002

Data Index: 782258 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1545. Min Act: -0.0002

Data Index: 1326400 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1518. Min Act: -0.0002

Data Index: 504206 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1619. Min Act: -0.0002

Data Index: 16393 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1567. Min Act: -0.0002

Data Index: 665652 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1502. Min Act: -0.0002

Data Index: 1336447 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1512. Min Act: -0.0002

Data Index: 1086874 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1492. Min Act: -0.0002

Data Index: 359660 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1499. Min Act: -0.0002

Data Index: 726333 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1438. Min Act: -0.0002

Data Index: 816906 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1422. Min Act: -0.0002

Data Index: 915895 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1457. Min Act: -0.0002

Data Index: 246772 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1396. Min Act: -0.0002

Data Index: 144971 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1426. Min Act: -0.0002

Data Index: 4771 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1430. Min Act: -0.0002

Data Index: 740125 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1368. Min Act: -0.0002

Data Index: 600770 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1463. Min Act: -0.0002

Data Index: 124 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1402. Min Act: -0.0002

Data Index: 649878 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1456. Min Act: -0.0002

Data Index: 769063 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1364. Min Act: -0.0002

Data Index: 69794 (C4 (Web Text))

Max Activating Token Index: 161