Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4950 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1048476 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1291633 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1680. Min Act: -0.0000

Data Index: 294220 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1805. Min Act: -0.0000

Data Index: 492093 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1457. Min Act: -0.0000

Data Index: 601697 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1534. Min Act: -0.0000

Data Index: 294060 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1573. Min Act: -0.0000

Data Index: 410868 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1510. Min Act: -0.0000

Data Index: 918644 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1540. Min Act: -0.0000

Data Index: 452048 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1123698 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1000680 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1466. Min Act: -0.0000

Data Index: 702690 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1515. Min Act: -0.0000

Data Index: 788393 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1506. Min Act: -0.0001

Data Index: 50482 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1534. Min Act: -0.0000

Data Index: 605376 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1533. Min Act: -0.0000

Data Index: 461339 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1572. Min Act: -0.0000

Data Index: 987968 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1506. Min Act: -0.0000

Data Index: 6240 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1400. Min Act: -0.0000

Data Index: 696056 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1407. Min Act: -0.0000

Data Index: 654672 (C4 (Web Text))

Max Activating Token Index: 52