Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3355 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1834. Min Act: -0.0000

Data Index: 641762 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1181573 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1077105 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1599. Min Act: -0.0000

Data Index: 618437 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1448. Min Act: -0.0000

Data Index: 772609 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1255081 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1524. Min Act: -0.0000

Data Index: 737247 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1513. Min Act: -0.0000

Data Index: 378694 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1297060 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1436. Min Act: -0.0000

Data Index: 973208 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1486. Min Act: -0.0000

Data Index: 558993 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1009488 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1466. Min Act: -0.0000

Data Index: 68693 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1399. Min Act: -0.0000

Data Index: 899161 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1224259 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1439. Min Act: -0.0000

Data Index: 459831 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1355338 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1375. Min Act: -0.0000

Data Index: 674328 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1116610 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1359. Min Act: -0.0000

Data Index: 603402 (C4 (Web Text))

Max Activating Token Index: 957