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

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

Neuron 971 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1634. Min Act: -0.0000

Data Index: 749416 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1584. Min Act: -0.0000

Data Index: 1357350 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1573. Min Act: -0.0000

Data Index: 911126 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1512. Min Act: -0.0000

Data Index: 390376 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1471. Min Act: -0.0000

Data Index: 63794 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1322964 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1439. Min Act: -0.0000

Data Index: 648373 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1085664 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1409. Min Act: -0.0000

Data Index: 486856 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1377. Min Act: -0.0000

Data Index: 862695 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1563146 (Python Code)

Max Activating Token Index: 496

Text #11

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1544464 (Python Code)

Max Activating Token Index: 378

Text #12

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1654567 (Python Code)

Max Activating Token Index: 379

Text #13

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1387255 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1352756 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1321. Min Act: -0.0000

Data Index: 222327 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1280. Min Act: -0.0000

Data Index: 76551 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1317. Min Act: -0.0000

Data Index: 880474 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1271. Min Act: -0.0000

Data Index: 833299 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1349. Min Act: -0.0000

Data Index: 854740 (C4 (Web Text))

Max Activating Token Index: 716