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

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

Neuron 1500 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: 0.1846. Min Range: -0.1846

Max Act: 0.1806. Min Act: -0.0002

Data Index: 1212331 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1846. Min Act: -0.0002

Data Index: 1231126 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1752. Min Act: -0.0002

Data Index: 828495 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1760. Min Act: -0.0002

Data Index: 426111 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1664. Min Act: -0.0002

Data Index: 209997 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1566. Min Act: -0.0002

Data Index: 771043 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1592. Min Act: -0.0002

Data Index: 568471 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1640. Min Act: -0.0002

Data Index: 1168982 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1618. Min Act: -0.0002

Data Index: 852831 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1460. Min Act: -0.0002

Data Index: 739628 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1477. Min Act: -0.0002

Data Index: 356546 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1402. Min Act: -0.0002

Data Index: 474881 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1493. Min Act: -0.0002

Data Index: 1168334 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1440. Min Act: -0.0002

Data Index: 1108585 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1458. Min Act: -0.0002

Data Index: 1359293 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1444. Min Act: -0.0002

Data Index: 630797 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1413. Min Act: -0.0002

Data Index: 777011 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1415. Min Act: -0.0002

Data Index: 501667 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1396. Min Act: -0.0002

Data Index: 222577 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1347. Min Act: -0.0002

Data Index: 461008 (C4 (Web Text))

Max Activating Token Index: 220